| Message ID | 20220203215315.3285202-1-goldstein.w.n@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v1] x86: Reformat code in svml_s_atanhf16_core_avx512.S | expand |
Hi Noah, Since this patch is about glibc assembly language formatting, it may be helpful to everyone, if there is a section for glibc assembly coding in manual. https://sourceware.org/glibc/wiki/Style_and_Conventions You may also consider putting your tool in glibc code base, so that people can easily find/use it to check/format their assembly code. https://github.com/goldsteinn/assembly-beautifier Thank, Sunil On Thu, Feb 3, 2022 at 2:00 PM Noah Goldstein via Libc-alpha <libc-alpha@sourceware.org> wrote: > > Reformats to match style of other hand coded assembly files. > > The changes are: > 1. Replace 8x space with tab before instructions. > 2. After instruction len < 8 use tab. > 3. After instruction len >= 8 use space. > 4. 1 Space after comma between instruction operands. > 5. Indent comments similiar with code. > 6. Make comments complete sentences. > 7. Tab after '#define' > 8. Spaces at '#' representing the depth. > > The final executable is unchanged by this commit. > --- > The changes for this patch where made with the following > script: https://github.com/goldsteinn/assembly-beautifier > > The goal of this patch is just to reformat the code > so it is more human friendly and try create a style > that future patches will be based on. > > If this patch is accepted ensuing patches to > optimize the performance of svml_s_atanhf16_core_avx512.S > will be based on this patch. > > .../multiarch/svml_s_atanhf16_core_avx512.S | 655 +++++++++--------- > 1 file changed, 321 insertions(+), 334 deletions(-) > > diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > index f863f4f959..ed90a427a6 100644 > --- a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > @@ -33,361 +33,348 @@ > > /* Offsets for data table __svml_satanh_data_internal_avx512 > */ > -#define Log_tbl_H 0 > -#define Log_tbl_L 128 > -#define One 256 > -#define AbsMask 320 > -#define AddB5 384 > -#define RcpBitMask 448 > -#define poly_coeff3 512 > -#define poly_coeff2 576 > -#define poly_coeff1 640 > -#define poly_coeff0 704 > -#define Half 768 > -#define L2H 832 > -#define L2L 896 > +#define Log_tbl_H 0 > +#define Log_tbl_L 128 > +#define One 256 > +#define AbsMask 320 > +#define AddB5 384 > +#define RcpBitMask 448 > +#define poly_coeff3 512 > +#define poly_coeff2 576 > +#define poly_coeff1 640 > +#define poly_coeff0 704 > +#define Half 768 > +#define L2H 832 > +#define L2L 896 > > #include <sysdep.h> > > - .text > - .section .text.exex512,"ax",@progbits > + .text > + .section .text.exex512, "ax", @progbits > ENTRY(_ZGVeN16v_atanhf_skx) > - pushq %rbp > - cfi_def_cfa_offset(16) > - movq %rsp, %rbp > - cfi_def_cfa(6, 16) > - cfi_offset(6, -16) > - andq $-64, %rsp > - subq $192, %rsp > - vmovups One+__svml_satanh_data_internal_avx512(%rip), %zmm4 > - > -/* round reciprocals to 1+5b mantissas */ > - vmovups AddB5+__svml_satanh_data_internal_avx512(%rip), %zmm14 > - vmovups RcpBitMask+__svml_satanh_data_internal_avx512(%rip), %zmm1 > - vmovaps %zmm0, %zmm11 > - vandps AbsMask+__svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > - > -/* 1+y */ > - vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > - > -/* 1-y */ > - vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > - vxorps %zmm6, %zmm11, %zmm10 > - > -/* Yp_high */ > - vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > - > -/* -Ym_high */ > - vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > - > -/* RcpP ~ 1/Yp */ > - vrcp14ps %zmm9, %zmm12 > - > -/* RcpM ~ 1/Ym */ > - vrcp14ps %zmm8, %zmm13 > - > -/* input outside (-1, 1) ? */ > - vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > - vpaddd %zmm14, %zmm12, %zmm15 > - vpaddd %zmm14, %zmm13, %zmm0 > - > -/* Yp_low */ > - vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > - vandps %zmm1, %zmm15, %zmm7 > - vandps %zmm1, %zmm0, %zmm12 > - > -/* Ym_low */ > - vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > - > -/* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low */ > - vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > - > -/* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low */ > - vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > - vmovups Log_tbl_L+__svml_satanh_data_internal_avx512(%rip), %zmm8 > - vmovups Log_tbl_L+64+__svml_satanh_data_internal_avx512(%rip), %zmm13 > - > -/* exponents */ > - vgetexpps {sae}, %zmm7, %zmm15 > - vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > - > -/* Table lookups */ > - vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > - vgetexpps {sae}, %zmm12, %zmm14 > - vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > - > -/* Prepare table index */ > - vpsrld $18, %zmm7, %zmm3 > - vpsrld $18, %zmm12, %zmm2 > - vmovups Log_tbl_H+64+__svml_satanh_data_internal_avx512(%rip), %zmm7 > - vmovups poly_coeff1+__svml_satanh_data_internal_avx512(%rip), %zmm12 > - > -/* Km-Kp */ > - vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > - kmovw %k0, %edx > - vmovaps %zmm3, %zmm0 > - vpermi2ps %zmm13, %zmm8, %zmm3 > - vpermt2ps %zmm13, %zmm2, %zmm8 > - vpermi2ps %zmm7, %zmm6, %zmm0 > - vpermt2ps %zmm7, %zmm2, %zmm6 > - vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > - > -/* K*L2H + Th */ > - vmovups L2H+__svml_satanh_data_internal_avx512(%rip), %zmm2 > - > -/* K*L2L + Tl */ > - vmovups L2L+__svml_satanh_data_internal_avx512(%rip), %zmm3 > - > -/* polynomials */ > - vmovups poly_coeff3+__svml_satanh_data_internal_avx512(%rip), %zmm7 > - vmovups poly_coeff0+__svml_satanh_data_internal_avx512(%rip), %zmm13 > - > -/* table values */ > - vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > - vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > - vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > - vmovups poly_coeff2+__svml_satanh_data_internal_avx512(%rip), %zmm3 > - vmovaps %zmm3, %zmm2 > - vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > - vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > - vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > - vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > - vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > - vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > - > -/* (K*L2L + Tl) + Rp*PolyP */ > - vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > - vorps Half+__svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > - > -/* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM */ > - vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > - vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > - vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > - testl %edx, %edx > - > -/* Go to special inputs processing branch */ > - jne L(SPECIAL_VALUES_BRANCH) > - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm11 > - > -/* Restore registers > - * and exit the function > - */ > + pushq %rbp > + cfi_def_cfa_offset (16) > + movq %rsp, %rbp > + cfi_def_cfa (6, 16) > + cfi_offset (6, -16) > + andq $-64, %rsp > + subq $192, %rsp > + vmovups One + __svml_satanh_data_internal_avx512(%rip), %zmm4 > + > + /* round reciprocals to 1+5b mantissas. */ > + vmovups AddB5 + __svml_satanh_data_internal_avx512(%rip), %zmm14 > + vmovups RcpBitMask + __svml_satanh_data_internal_avx512(%rip), %zmm1 > + vmovaps %zmm0, %zmm11 > + vandps AbsMask + __svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > + > + /* 1+y. */ > + vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > + > + /* 1-y. */ > + vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > + vxorps %zmm6, %zmm11, %zmm10 > + > + /* Yp_high. */ > + vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > + > + /* -Ym_high. */ > + vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > + > + /* RcpP ~ 1/Yp. */ > + vrcp14ps %zmm9, %zmm12 > + > + /* RcpM ~ 1/Ym. */ > + vrcp14ps %zmm8, %zmm13 > + > + /* input outside (-1, 1) ?. */ > + vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > + vpaddd %zmm14, %zmm12, %zmm15 > + vpaddd %zmm14, %zmm13, %zmm0 > + > + /* Yp_low. */ > + vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > + vandps %zmm1, %zmm15, %zmm7 > + vandps %zmm1, %zmm0, %zmm12 > + > + /* Ym_low. */ > + vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > + > + /* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low. */ > + vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > + > + /* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low. */ > + vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > + vmovups Log_tbl_L + __svml_satanh_data_internal_avx512(%rip), %zmm8 > + vmovups Log_tbl_L + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > + > + /* exponents. */ > + vgetexpps {sae}, %zmm7, %zmm15 > + vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > + > + /* Table lookups. */ > + vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > + vgetexpps {sae}, %zmm12, %zmm14 > + vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > + > + /* Prepare table index. */ > + vpsrld $18, %zmm7, %zmm3 > + vpsrld $18, %zmm12, %zmm2 > + vmovups Log_tbl_H + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > + vmovups poly_coeff1 + __svml_satanh_data_internal_avx512(%rip), %zmm12 > + > + /* Km-Kp. */ > + vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > + kmovw %k0, %edx > + vmovaps %zmm3, %zmm0 > + vpermi2ps %zmm13, %zmm8, %zmm3 > + vpermt2ps %zmm13, %zmm2, %zmm8 > + vpermi2ps %zmm7, %zmm6, %zmm0 > + vpermt2ps %zmm7, %zmm2, %zmm6 > + vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > + > + /* K*L2H + Th. */ > + vmovups L2H + __svml_satanh_data_internal_avx512(%rip), %zmm2 > + > + /* K*L2L + Tl. */ > + vmovups L2L + __svml_satanh_data_internal_avx512(%rip), %zmm3 > + > + /* polynomials. */ > + vmovups poly_coeff3 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > + vmovups poly_coeff0 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > + > + /* table values. */ > + vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > + vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > + vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > + vmovups poly_coeff2 + __svml_satanh_data_internal_avx512(%rip), %zmm3 > + vmovaps %zmm3, %zmm2 > + vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > + vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > + vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > + vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > + vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > + vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > + > + /* (K*L2L + Tl) + Rp*PolyP. */ > + vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > + vorps Half + __svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > + > + /* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM. */ > + vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > + vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > + vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > + testl %edx, %edx > + > + /* Go to special inputs processing branch. */ > + jne L(SPECIAL_VALUES_BRANCH) > + > + /* Restore registers * and exit the function. */ > > L(EXIT): > - movq %rbp, %rsp > - popq %rbp > - cfi_def_cfa(7, 8) > - cfi_restore(6) > - ret > - cfi_def_cfa(6, 16) > - cfi_offset(6, -16) > - > -/* Branch to process > - * special inputs > - */ > + movq %rbp, %rsp > + popq %rbp > + cfi_def_cfa (7, 8) > + cfi_restore (6) > + ret > + cfi_def_cfa (6, 16) > + cfi_offset (6, -16) > + > + /* Branch to process special inputs. */ > > L(SPECIAL_VALUES_BRANCH): > - vmovups %zmm11, 64(%rsp) > - vmovups %zmm0, 128(%rsp) > - # LOE rbx r12 r13 r14 r15 edx zmm0 > - > - xorl %eax, %eax > - # LOE rbx r12 r13 r14 r15 eax edx > - > - vzeroupper > - movq %r12, 16(%rsp) > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > - movl %eax, %r12d > - movq %r13, 8(%rsp) > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > - movl %edx, %r13d > - movq %r14, (%rsp) > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > - # LOE rbx r15 r12d r13d > - > -/* Range mask > - * bits check > - */ > + vmovups %zmm11, 64(%rsp) > + vmovups %zmm0, 128(%rsp) > + > + xorl %eax, %eax > + > + vzeroupper > + movq %r12, 16(%rsp) > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > + movl %eax, %r12d > + movq %r13, 8(%rsp) > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > + movl %edx, %r13d > + movq %r14, (%rsp) > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > + > + /* Range mask * bits check. */ > > L(RANGEMASK_CHECK): > - btl %r12d, %r13d > + btl %r12d, %r13d > > -/* Call scalar math function */ > - jc L(SCALAR_MATH_CALL) > - # LOE rbx r15 r12d r13d > + /* Call scalar math function. */ > + jc L(SCALAR_MATH_CALL) > > -/* Special inputs > - * processing loop > - */ > + /* Special inputs processing loop. */ > > L(SPECIAL_VALUES_LOOP): > - incl %r12d > - cmpl $16, %r12d > - > -/* Check bits in range mask */ > - jl L(RANGEMASK_CHECK) > - # LOE rbx r15 r12d r13d > - > - movq 16(%rsp), %r12 > - cfi_restore(12) > - movq 8(%rsp), %r13 > - cfi_restore(13) > - movq (%rsp), %r14 > - cfi_restore(14) > - vmovups 128(%rsp), %zmm0 > - > -/* Go to exit */ > - jmp L(EXIT) > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > - # LOE rbx r12 r13 r14 r15 zmm0 > - > -/* Scalar math fucntion call > - * to process special input > - */ > + incl %r12d > + cmpl $16, %r12d > + > + /* Check bits in range mask. */ > + jl L(RANGEMASK_CHECK) > + > + movq 16(%rsp), %r12 > + cfi_restore (12) > + movq 8(%rsp), %r13 > + cfi_restore (13) > + movq (%rsp), %r14 > + cfi_restore (14) > + vmovups 128(%rsp), %zmm0 > + > + /* Go to exit. */ > + jmp L(EXIT) > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > + > + /* Scalar math fucntion call to process special input. */ > > L(SCALAR_MATH_CALL): > - movl %r12d, %r14d > - movss 64(%rsp,%r14,4), %xmm0 > - call atanhf@PLT > - # LOE rbx r14 r15 r12d r13d xmm0 > + movl %r12d, %r14d > + movss 64(%rsp, %r14, 4), %xmm0 > + call atanhf@PLT > > - movss %xmm0, 128(%rsp,%r14,4) > + movss %xmm0, 128(%rsp, %r14, 4) > > -/* Process special inputs in loop */ > - jmp L(SPECIAL_VALUES_LOOP) > - # LOE rbx r15 r12d r13d > + /* Process special inputs in loop. */ > + jmp L(SPECIAL_VALUES_LOOP) > END(_ZGVeN16v_atanhf_skx) > > - .section .rodata, "a" > - .align 64 > + .section .rodata, "a" > + .align 64 > > #ifdef __svml_satanh_data_internal_avx512_typedef > -typedef unsigned int VUINT32; > -typedef struct { > - __declspec(align(64)) VUINT32 Log_tbl_H[32][1]; > - __declspec(align(64)) VUINT32 Log_tbl_L[32][1]; > - __declspec(align(64)) VUINT32 One[16][1]; > - __declspec(align(64)) VUINT32 AbsMask[16][1]; > - __declspec(align(64)) VUINT32 AddB5[16][1]; > - __declspec(align(64)) VUINT32 RcpBitMask[16][1]; > - __declspec(align(64)) VUINT32 poly_coeff3[16][1]; > - __declspec(align(64)) VUINT32 poly_coeff2[16][1]; > - __declspec(align(64)) VUINT32 poly_coeff1[16][1]; > - __declspec(align(64)) VUINT32 poly_coeff0[16][1]; > - __declspec(align(64)) VUINT32 Half[16][1]; > - __declspec(align(64)) VUINT32 L2H[16][1]; > - __declspec(align(64)) VUINT32 L2L[16][1]; > - } __svml_satanh_data_internal_avx512; > + typedef unsigned int VUINT32; > + typedef struct{ > + __declspec (align(64))VUINT32 Log_tbl_H[32][1]; > + __declspec (align(64))VUINT32 Log_tbl_L[32][1]; > + __declspec (align(64))VUINT32 One[16][1]; > + __declspec (align(64))VUINT32 AbsMask[16][1]; > + __declspec (align(64))VUINT32 AddB5[16][1]; > + __declspec (align(64))VUINT32 RcpBitMask[16][1]; > + __declspec (align(64))VUINT32 poly_coeff3[16][1]; > + __declspec (align(64))VUINT32 poly_coeff2[16][1]; > + __declspec (align(64))VUINT32 poly_coeff1[16][1]; > + __declspec (align(64))VUINT32 poly_coeff0[16][1]; > + __declspec (align(64))VUINT32 Half[16][1]; > + __declspec (align(64))VUINT32 L2H[16][1]; > + __declspec (align(64))VUINT32 L2L[16][1]; > + }__svml_satanh_data_internal_avx512; > #endif > __svml_satanh_data_internal_avx512: > - /*== Log_tbl_H ==*/ > - .long 0x00000000 > - .long 0x3cfc0000 > - .long 0x3d780000 > - .long 0x3db78000 > - .long 0x3df10000 > - .long 0x3e14c000 > - .long 0x3e300000 > - .long 0x3e4a8000 > - .long 0x3e648000 > - .long 0x3e7dc000 > - .long 0x3e8b4000 > - .long 0x3e974000 > - .long 0x3ea30000 > - .long 0x3eae8000 > - .long 0x3eb9c000 > - .long 0x3ec4e000 > - .long 0x3ecfa000 > - .long 0x3eda2000 > - .long 0x3ee48000 > - .long 0x3eeea000 > - .long 0x3ef8a000 > - .long 0x3f013000 > - .long 0x3f05f000 > - .long 0x3f0aa000 > - .long 0x3f0f4000 > - .long 0x3f13d000 > - .long 0x3f184000 > - .long 0x3f1ca000 > - .long 0x3f20f000 > - .long 0x3f252000 > - .long 0x3f295000 > - .long 0x3f2d7000 > - /*== Log_tbl_L ==*/ > - .align 64 > - .long 0x00000000 > - .long 0x3726c39e > - .long 0x38a30c01 > - .long 0x37528ae5 > - .long 0x38e0edc5 > - .long 0xb8ab41f8 > - .long 0xb7cf8f58 > - .long 0x3896a73d > - .long 0xb5838656 > - .long 0x380c36af > - .long 0xb8235454 > - .long 0x3862bae1 > - .long 0x38c5e10e > - .long 0x38dedfac > - .long 0x38ebfb5e > - .long 0xb8e63c9f > - .long 0xb85c1340 > - .long 0x38777bcd > - .long 0xb6038656 > - .long 0x37d40984 > - .long 0xb8b85028 > - .long 0xb8ad5a5a > - .long 0x3865c84a > - .long 0x38c3d2f5 > - .long 0x383ebce1 > - .long 0xb8a1ed76 > - .long 0xb7a332c4 > - .long 0xb779654f > - .long 0xb8602f73 > - .long 0x38f85db0 > - .long 0x37b4996f > - .long 0xb8bfb3ca > - /*== One ==*/ > - .align 64 > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > - /*== AbsMask ==*/ > - .align 64 > - .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > - /*== AddB5 ==*/ > - .align 64 > - .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > - /*== RcpBitMask ==*/ > - .align 64 > - .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > - /*== poly_coeff3 ==*/ > - .align 64 > - .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > - /*== poly_coeff2 ==*/ > - .align 64 > - .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > - /*== poly_coeff1 ==*/ > - .align 64 > - .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > - /*== poly_coeff0 ==*/ > - .align 64 > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > - /*== Half ==*/ > - .align 64 > - .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > - /*== L2H = log(2)_high ==*/ > - .align 64 > - .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > - /*== L2L = log(2)_low ==*/ > - .align 64 > - .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > - .align 64 > - .type __svml_satanh_data_internal_avx512,@object > - .size __svml_satanh_data_internal_avx512,.-__svml_satanh_data_internal_avx512 > + /* == Log_tbl_H ==. */ > + .long 0x00000000 > + .long 0x3cfc0000 > + .long 0x3d780000 > + .long 0x3db78000 > + .long 0x3df10000 > + .long 0x3e14c000 > + .long 0x3e300000 > + .long 0x3e4a8000 > + .long 0x3e648000 > + .long 0x3e7dc000 > + .long 0x3e8b4000 > + .long 0x3e974000 > + .long 0x3ea30000 > + .long 0x3eae8000 > + .long 0x3eb9c000 > + .long 0x3ec4e000 > + .long 0x3ecfa000 > + .long 0x3eda2000 > + .long 0x3ee48000 > + .long 0x3eeea000 > + .long 0x3ef8a000 > + .long 0x3f013000 > + .long 0x3f05f000 > + .long 0x3f0aa000 > + .long 0x3f0f4000 > + .long 0x3f13d000 > + .long 0x3f184000 > + .long 0x3f1ca000 > + .long 0x3f20f000 > + .long 0x3f252000 > + .long 0x3f295000 > + .long 0x3f2d7000 > + /* == Log_tbl_L ==. */ > + .align 64 > + .long 0x00000000 > + .long 0x3726c39e > + .long 0x38a30c01 > + .long 0x37528ae5 > + .long 0x38e0edc5 > + .long 0xb8ab41f8 > + .long 0xb7cf8f58 > + .long 0x3896a73d > + .long 0xb5838656 > + .long 0x380c36af > + .long 0xb8235454 > + .long 0x3862bae1 > + .long 0x38c5e10e > + .long 0x38dedfac > + .long 0x38ebfb5e > + .long 0xb8e63c9f > + .long 0xb85c1340 > + .long 0x38777bcd > + .long 0xb6038656 > + .long 0x37d40984 > + .long 0xb8b85028 > + .long 0xb8ad5a5a > + .long 0x3865c84a > + .long 0x38c3d2f5 > + .long 0x383ebce1 > + .long 0xb8a1ed76 > + .long 0xb7a332c4 > + .long 0xb779654f > + .long 0xb8602f73 > + .long 0x38f85db0 > + .long 0x37b4996f > + .long 0xb8bfb3ca > + /* == One ==. */ > + .align 64 > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > + /* == AbsMask ==. */ > + .align 64 > + .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > + /* == AddB5 ==. */ > + .align 64 > + .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > + /* == RcpBitMask ==. */ > + .align 64 > + .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > + /* == poly_coeff3 ==. */ > + .align 64 > + .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > + /* == poly_coeff2 ==. */ > + .align 64 > + .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > + /* == poly_coeff1 ==. */ > + .align 64 > + .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > + /* == poly_coeff0 ==. */ > + .align 64 > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > + /* == Half ==. */ > + .align 64 > + .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > + /* == L2H = log(2)_high ==. */ > + .align 64 > + .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > + /* == L2L = log(2)_low ==. */ > + .align 64 > + .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > + .align 64 > + .type __svml_satanh_data_internal_avx512, @object > + .size __svml_satanh_data_internal_avx512, .-__svml_satanh_data_internal_avx512 > -- > 2.25.1 >
On Sat, Feb 5, 2022 at 2:01 AM Sunil Pandey <skpgkp2@gmail.com> wrote: > > Hi Noah, > > Since this patch is about glibc assembly language formatting, it may be > helpful to everyone, if there is a section for glibc assembly coding > in manual. > > https://sourceware.org/glibc/wiki/Style_and_Conventions > > You may also consider putting your tool in glibc code base, so that people > can easily find/use it to check/format their assembly code. Like the idea. How does the following sound: == x86 GAS (Assembly) == The following are stylistic conventions for x86 GAS contributions. Other style conventions that are relevant to x86 GAS syntax are also included (i.e column limit, indenting preprocessor directives, etc..). 1. Instructions should be proceeded by a tab. 2. Instruction less than 8 characters in length should have a tab between it and the first operand. 3. Instruction greater than 7 characters in length should have a space between it and the first operand. 4. There should be a space after the comma seperating operands. For example for rules 1, 2, 3, and 4: ``` /* <tab><short instruction><tab><op0><comma><space><op1>. */ addl $1, %eax /* <tab><long instruction><space><op0><comma><space><op1>. */ vpmovmaskb %ymm0, %eax ``` 5. Comments should be indented with code: For example for rule 5: ``` /* Function XYZ returns. */ ENTRY(XYZ) /* Return from XYZ. */ ret END(XYZ) ``` 6. Tab after `#define`d names and their value. For example: ``` /* No value for 'HELLO' so no tab afterwards. */ #define HELLO /* Value for 'WORLD' so tab separated 'WORLD' from '10'. */ #define WORLD 10 ``` > > https://github.com/goldsteinn/assembly-beautifier Thats not an official tool. Its code quality is not really up to standard and I can't really commit to maintaining it. If its improved to a state where its good enough for GLIBC I'll post a patch. > > Thank, > Sunil > > On Thu, Feb 3, 2022 at 2:00 PM Noah Goldstein via Libc-alpha > <libc-alpha@sourceware.org> wrote: > > > > Reformats to match style of other hand coded assembly files. > > > > The changes are: > > 1. Replace 8x space with tab before instructions. > > 2. After instruction len < 8 use tab. > > 3. After instruction len >= 8 use space. > > 4. 1 Space after comma between instruction operands. > > 5. Indent comments similiar with code. > > 6. Make comments complete sentences. > > 7. Tab after '#define' > > 8. Spaces at '#' representing the depth. > > > > The final executable is unchanged by this commit. > > --- > > The changes for this patch where made with the following > > script: https://github.com/goldsteinn/assembly-beautifier > > > > The goal of this patch is just to reformat the code > > so it is more human friendly and try create a style > > that future patches will be based on. > > > > If this patch is accepted ensuing patches to > > optimize the performance of svml_s_atanhf16_core_avx512.S > > will be based on this patch. > > > > .../multiarch/svml_s_atanhf16_core_avx512.S | 655 +++++++++--------- > > 1 file changed, 321 insertions(+), 334 deletions(-) > > > > diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > index f863f4f959..ed90a427a6 100644 > > --- a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > @@ -33,361 +33,348 @@ > > > > /* Offsets for data table __svml_satanh_data_internal_avx512 > > */ > > -#define Log_tbl_H 0 > > -#define Log_tbl_L 128 > > -#define One 256 > > -#define AbsMask 320 > > -#define AddB5 384 > > -#define RcpBitMask 448 > > -#define poly_coeff3 512 > > -#define poly_coeff2 576 > > -#define poly_coeff1 640 > > -#define poly_coeff0 704 > > -#define Half 768 > > -#define L2H 832 > > -#define L2L 896 > > +#define Log_tbl_H 0 > > +#define Log_tbl_L 128 > > +#define One 256 > > +#define AbsMask 320 > > +#define AddB5 384 > > +#define RcpBitMask 448 > > +#define poly_coeff3 512 > > +#define poly_coeff2 576 > > +#define poly_coeff1 640 > > +#define poly_coeff0 704 > > +#define Half 768 > > +#define L2H 832 > > +#define L2L 896 > > > > #include <sysdep.h> > > > > - .text > > - .section .text.exex512,"ax",@progbits > > + .text > > + .section .text.exex512, "ax", @progbits > > ENTRY(_ZGVeN16v_atanhf_skx) > > - pushq %rbp > > - cfi_def_cfa_offset(16) > > - movq %rsp, %rbp > > - cfi_def_cfa(6, 16) > > - cfi_offset(6, -16) > > - andq $-64, %rsp > > - subq $192, %rsp > > - vmovups One+__svml_satanh_data_internal_avx512(%rip), %zmm4 > > - > > -/* round reciprocals to 1+5b mantissas */ > > - vmovups AddB5+__svml_satanh_data_internal_avx512(%rip), %zmm14 > > - vmovups RcpBitMask+__svml_satanh_data_internal_avx512(%rip), %zmm1 > > - vmovaps %zmm0, %zmm11 > > - vandps AbsMask+__svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > > - > > -/* 1+y */ > > - vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > > - > > -/* 1-y */ > > - vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > > - vxorps %zmm6, %zmm11, %zmm10 > > - > > -/* Yp_high */ > > - vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > > - > > -/* -Ym_high */ > > - vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > > - > > -/* RcpP ~ 1/Yp */ > > - vrcp14ps %zmm9, %zmm12 > > - > > -/* RcpM ~ 1/Ym */ > > - vrcp14ps %zmm8, %zmm13 > > - > > -/* input outside (-1, 1) ? */ > > - vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > > - vpaddd %zmm14, %zmm12, %zmm15 > > - vpaddd %zmm14, %zmm13, %zmm0 > > - > > -/* Yp_low */ > > - vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > > - vandps %zmm1, %zmm15, %zmm7 > > - vandps %zmm1, %zmm0, %zmm12 > > - > > -/* Ym_low */ > > - vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > > - > > -/* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low */ > > - vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > > - > > -/* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low */ > > - vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > > - vmovups Log_tbl_L+__svml_satanh_data_internal_avx512(%rip), %zmm8 > > - vmovups Log_tbl_L+64+__svml_satanh_data_internal_avx512(%rip), %zmm13 > > - > > -/* exponents */ > > - vgetexpps {sae}, %zmm7, %zmm15 > > - vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > > - > > -/* Table lookups */ > > - vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > > - vgetexpps {sae}, %zmm12, %zmm14 > > - vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > > - > > -/* Prepare table index */ > > - vpsrld $18, %zmm7, %zmm3 > > - vpsrld $18, %zmm12, %zmm2 > > - vmovups Log_tbl_H+64+__svml_satanh_data_internal_avx512(%rip), %zmm7 > > - vmovups poly_coeff1+__svml_satanh_data_internal_avx512(%rip), %zmm12 > > - > > -/* Km-Kp */ > > - vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > > - kmovw %k0, %edx > > - vmovaps %zmm3, %zmm0 > > - vpermi2ps %zmm13, %zmm8, %zmm3 > > - vpermt2ps %zmm13, %zmm2, %zmm8 > > - vpermi2ps %zmm7, %zmm6, %zmm0 > > - vpermt2ps %zmm7, %zmm2, %zmm6 > > - vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > > - > > -/* K*L2H + Th */ > > - vmovups L2H+__svml_satanh_data_internal_avx512(%rip), %zmm2 > > - > > -/* K*L2L + Tl */ > > - vmovups L2L+__svml_satanh_data_internal_avx512(%rip), %zmm3 > > - > > -/* polynomials */ > > - vmovups poly_coeff3+__svml_satanh_data_internal_avx512(%rip), %zmm7 > > - vmovups poly_coeff0+__svml_satanh_data_internal_avx512(%rip), %zmm13 > > - > > -/* table values */ > > - vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > > - vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > > - vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > > - vmovups poly_coeff2+__svml_satanh_data_internal_avx512(%rip), %zmm3 > > - vmovaps %zmm3, %zmm2 > > - vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > > - vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > > - vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > > - vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > > - vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > > - vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > > - > > -/* (K*L2L + Tl) + Rp*PolyP */ > > - vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > > - vorps Half+__svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > > - > > -/* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM */ > > - vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > > - vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > > - vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > > - testl %edx, %edx > > - > > -/* Go to special inputs processing branch */ > > - jne L(SPECIAL_VALUES_BRANCH) > > - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm11 > > - > > -/* Restore registers > > - * and exit the function > > - */ > > + pushq %rbp > > + cfi_def_cfa_offset (16) > > + movq %rsp, %rbp > > + cfi_def_cfa (6, 16) > > + cfi_offset (6, -16) > > + andq $-64, %rsp > > + subq $192, %rsp > > + vmovups One + __svml_satanh_data_internal_avx512(%rip), %zmm4 > > + > > + /* round reciprocals to 1+5b mantissas. */ > > + vmovups AddB5 + __svml_satanh_data_internal_avx512(%rip), %zmm14 > > + vmovups RcpBitMask + __svml_satanh_data_internal_avx512(%rip), %zmm1 > > + vmovaps %zmm0, %zmm11 > > + vandps AbsMask + __svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > > + > > + /* 1+y. */ > > + vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > > + > > + /* 1-y. */ > > + vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > > + vxorps %zmm6, %zmm11, %zmm10 > > + > > + /* Yp_high. */ > > + vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > > + > > + /* -Ym_high. */ > > + vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > > + > > + /* RcpP ~ 1/Yp. */ > > + vrcp14ps %zmm9, %zmm12 > > + > > + /* RcpM ~ 1/Ym. */ > > + vrcp14ps %zmm8, %zmm13 > > + > > + /* input outside (-1, 1) ?. */ > > + vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > > + vpaddd %zmm14, %zmm12, %zmm15 > > + vpaddd %zmm14, %zmm13, %zmm0 > > + > > + /* Yp_low. */ > > + vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > > + vandps %zmm1, %zmm15, %zmm7 > > + vandps %zmm1, %zmm0, %zmm12 > > + > > + /* Ym_low. */ > > + vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > > + > > + /* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low. */ > > + vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > > + > > + /* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low. */ > > + vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > > + vmovups Log_tbl_L + __svml_satanh_data_internal_avx512(%rip), %zmm8 > > + vmovups Log_tbl_L + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > > + > > + /* exponents. */ > > + vgetexpps {sae}, %zmm7, %zmm15 > > + vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > > + > > + /* Table lookups. */ > > + vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > > + vgetexpps {sae}, %zmm12, %zmm14 > > + vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > > + > > + /* Prepare table index. */ > > + vpsrld $18, %zmm7, %zmm3 > > + vpsrld $18, %zmm12, %zmm2 > > + vmovups Log_tbl_H + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > > + vmovups poly_coeff1 + __svml_satanh_data_internal_avx512(%rip), %zmm12 > > + > > + /* Km-Kp. */ > > + vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > > + kmovw %k0, %edx > > + vmovaps %zmm3, %zmm0 > > + vpermi2ps %zmm13, %zmm8, %zmm3 > > + vpermt2ps %zmm13, %zmm2, %zmm8 > > + vpermi2ps %zmm7, %zmm6, %zmm0 > > + vpermt2ps %zmm7, %zmm2, %zmm6 > > + vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > > + > > + /* K*L2H + Th. */ > > + vmovups L2H + __svml_satanh_data_internal_avx512(%rip), %zmm2 > > + > > + /* K*L2L + Tl. */ > > + vmovups L2L + __svml_satanh_data_internal_avx512(%rip), %zmm3 > > + > > + /* polynomials. */ > > + vmovups poly_coeff3 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > > + vmovups poly_coeff0 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > > + > > + /* table values. */ > > + vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > > + vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > > + vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > > + vmovups poly_coeff2 + __svml_satanh_data_internal_avx512(%rip), %zmm3 > > + vmovaps %zmm3, %zmm2 > > + vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > > + vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > > + vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > > + vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > > + vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > > + vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > > + > > + /* (K*L2L + Tl) + Rp*PolyP. */ > > + vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > > + vorps Half + __svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > > + > > + /* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM. */ > > + vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > > + vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > > + vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > > + testl %edx, %edx > > + > > + /* Go to special inputs processing branch. */ > > + jne L(SPECIAL_VALUES_BRANCH) > > + > > + /* Restore registers * and exit the function. */ > > > > L(EXIT): > > - movq %rbp, %rsp > > - popq %rbp > > - cfi_def_cfa(7, 8) > > - cfi_restore(6) > > - ret > > - cfi_def_cfa(6, 16) > > - cfi_offset(6, -16) > > - > > -/* Branch to process > > - * special inputs > > - */ > > + movq %rbp, %rsp > > + popq %rbp > > + cfi_def_cfa (7, 8) > > + cfi_restore (6) > > + ret > > + cfi_def_cfa (6, 16) > > + cfi_offset (6, -16) > > + > > + /* Branch to process special inputs. */ > > > > L(SPECIAL_VALUES_BRANCH): > > - vmovups %zmm11, 64(%rsp) > > - vmovups %zmm0, 128(%rsp) > > - # LOE rbx r12 r13 r14 r15 edx zmm0 > > - > > - xorl %eax, %eax > > - # LOE rbx r12 r13 r14 r15 eax edx > > - > > - vzeroupper > > - movq %r12, 16(%rsp) > > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > > - movl %eax, %r12d > > - movq %r13, 8(%rsp) > > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > > - movl %edx, %r13d > > - movq %r14, (%rsp) > > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > > - # LOE rbx r15 r12d r13d > > - > > -/* Range mask > > - * bits check > > - */ > > + vmovups %zmm11, 64(%rsp) > > + vmovups %zmm0, 128(%rsp) > > + > > + xorl %eax, %eax > > + > > + vzeroupper > > + movq %r12, 16(%rsp) > > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > > + movl %eax, %r12d > > + movq %r13, 8(%rsp) > > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > > + movl %edx, %r13d > > + movq %r14, (%rsp) > > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > > + > > + /* Range mask * bits check. */ > > > > L(RANGEMASK_CHECK): > > - btl %r12d, %r13d > > + btl %r12d, %r13d > > > > -/* Call scalar math function */ > > - jc L(SCALAR_MATH_CALL) > > - # LOE rbx r15 r12d r13d > > + /* Call scalar math function. */ > > + jc L(SCALAR_MATH_CALL) > > > > -/* Special inputs > > - * processing loop > > - */ > > + /* Special inputs processing loop. */ > > > > L(SPECIAL_VALUES_LOOP): > > - incl %r12d > > - cmpl $16, %r12d > > - > > -/* Check bits in range mask */ > > - jl L(RANGEMASK_CHECK) > > - # LOE rbx r15 r12d r13d > > - > > - movq 16(%rsp), %r12 > > - cfi_restore(12) > > - movq 8(%rsp), %r13 > > - cfi_restore(13) > > - movq (%rsp), %r14 > > - cfi_restore(14) > > - vmovups 128(%rsp), %zmm0 > > - > > -/* Go to exit */ > > - jmp L(EXIT) > > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > > - # LOE rbx r12 r13 r14 r15 zmm0 > > - > > -/* Scalar math fucntion call > > - * to process special input > > - */ > > + incl %r12d > > + cmpl $16, %r12d > > + > > + /* Check bits in range mask. */ > > + jl L(RANGEMASK_CHECK) > > + > > + movq 16(%rsp), %r12 > > + cfi_restore (12) > > + movq 8(%rsp), %r13 > > + cfi_restore (13) > > + movq (%rsp), %r14 > > + cfi_restore (14) > > + vmovups 128(%rsp), %zmm0 > > + > > + /* Go to exit. */ > > + jmp L(EXIT) > > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > > + > > + /* Scalar math fucntion call to process special input. */ > > > > L(SCALAR_MATH_CALL): > > - movl %r12d, %r14d > > - movss 64(%rsp,%r14,4), %xmm0 > > - call atanhf@PLT > > - # LOE rbx r14 r15 r12d r13d xmm0 > > + movl %r12d, %r14d > > + movss 64(%rsp, %r14, 4), %xmm0 > > + call atanhf@PLT > > > > - movss %xmm0, 128(%rsp,%r14,4) > > + movss %xmm0, 128(%rsp, %r14, 4) > > > > -/* Process special inputs in loop */ > > - jmp L(SPECIAL_VALUES_LOOP) > > - # LOE rbx r15 r12d r13d > > + /* Process special inputs in loop. */ > > + jmp L(SPECIAL_VALUES_LOOP) > > END(_ZGVeN16v_atanhf_skx) > > > > - .section .rodata, "a" > > - .align 64 > > + .section .rodata, "a" > > + .align 64 > > > > #ifdef __svml_satanh_data_internal_avx512_typedef > > -typedef unsigned int VUINT32; > > -typedef struct { > > - __declspec(align(64)) VUINT32 Log_tbl_H[32][1]; > > - __declspec(align(64)) VUINT32 Log_tbl_L[32][1]; > > - __declspec(align(64)) VUINT32 One[16][1]; > > - __declspec(align(64)) VUINT32 AbsMask[16][1]; > > - __declspec(align(64)) VUINT32 AddB5[16][1]; > > - __declspec(align(64)) VUINT32 RcpBitMask[16][1]; > > - __declspec(align(64)) VUINT32 poly_coeff3[16][1]; > > - __declspec(align(64)) VUINT32 poly_coeff2[16][1]; > > - __declspec(align(64)) VUINT32 poly_coeff1[16][1]; > > - __declspec(align(64)) VUINT32 poly_coeff0[16][1]; > > - __declspec(align(64)) VUINT32 Half[16][1]; > > - __declspec(align(64)) VUINT32 L2H[16][1]; > > - __declspec(align(64)) VUINT32 L2L[16][1]; > > - } __svml_satanh_data_internal_avx512; > > + typedef unsigned int VUINT32; > > + typedef struct{ > > + __declspec (align(64))VUINT32 Log_tbl_H[32][1]; > > + __declspec (align(64))VUINT32 Log_tbl_L[32][1]; > > + __declspec (align(64))VUINT32 One[16][1]; > > + __declspec (align(64))VUINT32 AbsMask[16][1]; > > + __declspec (align(64))VUINT32 AddB5[16][1]; > > + __declspec (align(64))VUINT32 RcpBitMask[16][1]; > > + __declspec (align(64))VUINT32 poly_coeff3[16][1]; > > + __declspec (align(64))VUINT32 poly_coeff2[16][1]; > > + __declspec (align(64))VUINT32 poly_coeff1[16][1]; > > + __declspec (align(64))VUINT32 poly_coeff0[16][1]; > > + __declspec (align(64))VUINT32 Half[16][1]; > > + __declspec (align(64))VUINT32 L2H[16][1]; > > + __declspec (align(64))VUINT32 L2L[16][1]; > > + }__svml_satanh_data_internal_avx512; > > #endif > > __svml_satanh_data_internal_avx512: > > - /*== Log_tbl_H ==*/ > > - .long 0x00000000 > > - .long 0x3cfc0000 > > - .long 0x3d780000 > > - .long 0x3db78000 > > - .long 0x3df10000 > > - .long 0x3e14c000 > > - .long 0x3e300000 > > - .long 0x3e4a8000 > > - .long 0x3e648000 > > - .long 0x3e7dc000 > > - .long 0x3e8b4000 > > - .long 0x3e974000 > > - .long 0x3ea30000 > > - .long 0x3eae8000 > > - .long 0x3eb9c000 > > - .long 0x3ec4e000 > > - .long 0x3ecfa000 > > - .long 0x3eda2000 > > - .long 0x3ee48000 > > - .long 0x3eeea000 > > - .long 0x3ef8a000 > > - .long 0x3f013000 > > - .long 0x3f05f000 > > - .long 0x3f0aa000 > > - .long 0x3f0f4000 > > - .long 0x3f13d000 > > - .long 0x3f184000 > > - .long 0x3f1ca000 > > - .long 0x3f20f000 > > - .long 0x3f252000 > > - .long 0x3f295000 > > - .long 0x3f2d7000 > > - /*== Log_tbl_L ==*/ > > - .align 64 > > - .long 0x00000000 > > - .long 0x3726c39e > > - .long 0x38a30c01 > > - .long 0x37528ae5 > > - .long 0x38e0edc5 > > - .long 0xb8ab41f8 > > - .long 0xb7cf8f58 > > - .long 0x3896a73d > > - .long 0xb5838656 > > - .long 0x380c36af > > - .long 0xb8235454 > > - .long 0x3862bae1 > > - .long 0x38c5e10e > > - .long 0x38dedfac > > - .long 0x38ebfb5e > > - .long 0xb8e63c9f > > - .long 0xb85c1340 > > - .long 0x38777bcd > > - .long 0xb6038656 > > - .long 0x37d40984 > > - .long 0xb8b85028 > > - .long 0xb8ad5a5a > > - .long 0x3865c84a > > - .long 0x38c3d2f5 > > - .long 0x383ebce1 > > - .long 0xb8a1ed76 > > - .long 0xb7a332c4 > > - .long 0xb779654f > > - .long 0xb8602f73 > > - .long 0x38f85db0 > > - .long 0x37b4996f > > - .long 0xb8bfb3ca > > - /*== One ==*/ > > - .align 64 > > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > - /*== AbsMask ==*/ > > - .align 64 > > - .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > > - /*== AddB5 ==*/ > > - .align 64 > > - .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > > - /*== RcpBitMask ==*/ > > - .align 64 > > - .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > > - /*== poly_coeff3 ==*/ > > - .align 64 > > - .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > > - /*== poly_coeff2 ==*/ > > - .align 64 > > - .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > > - /*== poly_coeff1 ==*/ > > - .align 64 > > - .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > > - /*== poly_coeff0 ==*/ > > - .align 64 > > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > - /*== Half ==*/ > > - .align 64 > > - .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > > - /*== L2H = log(2)_high ==*/ > > - .align 64 > > - .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > > - /*== L2L = log(2)_low ==*/ > > - .align 64 > > - .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > > - .align 64 > > - .type __svml_satanh_data_internal_avx512,@object > > - .size __svml_satanh_data_internal_avx512,.-__svml_satanh_data_internal_avx512 > > + /* == Log_tbl_H ==. */ > > + .long 0x00000000 > > + .long 0x3cfc0000 > > + .long 0x3d780000 > > + .long 0x3db78000 > > + .long 0x3df10000 > > + .long 0x3e14c000 > > + .long 0x3e300000 > > + .long 0x3e4a8000 > > + .long 0x3e648000 > > + .long 0x3e7dc000 > > + .long 0x3e8b4000 > > + .long 0x3e974000 > > + .long 0x3ea30000 > > + .long 0x3eae8000 > > + .long 0x3eb9c000 > > + .long 0x3ec4e000 > > + .long 0x3ecfa000 > > + .long 0x3eda2000 > > + .long 0x3ee48000 > > + .long 0x3eeea000 > > + .long 0x3ef8a000 > > + .long 0x3f013000 > > + .long 0x3f05f000 > > + .long 0x3f0aa000 > > + .long 0x3f0f4000 > > + .long 0x3f13d000 > > + .long 0x3f184000 > > + .long 0x3f1ca000 > > + .long 0x3f20f000 > > + .long 0x3f252000 > > + .long 0x3f295000 > > + .long 0x3f2d7000 > > + /* == Log_tbl_L ==. */ > > + .align 64 > > + .long 0x00000000 > > + .long 0x3726c39e > > + .long 0x38a30c01 > > + .long 0x37528ae5 > > + .long 0x38e0edc5 > > + .long 0xb8ab41f8 > > + .long 0xb7cf8f58 > > + .long 0x3896a73d > > + .long 0xb5838656 > > + .long 0x380c36af > > + .long 0xb8235454 > > + .long 0x3862bae1 > > + .long 0x38c5e10e > > + .long 0x38dedfac > > + .long 0x38ebfb5e > > + .long 0xb8e63c9f > > + .long 0xb85c1340 > > + .long 0x38777bcd > > + .long 0xb6038656 > > + .long 0x37d40984 > > + .long 0xb8b85028 > > + .long 0xb8ad5a5a > > + .long 0x3865c84a > > + .long 0x38c3d2f5 > > + .long 0x383ebce1 > > + .long 0xb8a1ed76 > > + .long 0xb7a332c4 > > + .long 0xb779654f > > + .long 0xb8602f73 > > + .long 0x38f85db0 > > + .long 0x37b4996f > > + .long 0xb8bfb3ca > > + /* == One ==. */ > > + .align 64 > > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > + /* == AbsMask ==. */ > > + .align 64 > > + .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > > + /* == AddB5 ==. */ > > + .align 64 > > + .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > > + /* == RcpBitMask ==. */ > > + .align 64 > > + .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > > + /* == poly_coeff3 ==. */ > > + .align 64 > > + .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > > + /* == poly_coeff2 ==. */ > > + .align 64 > > + .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > > + /* == poly_coeff1 ==. */ > > + .align 64 > > + .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > > + /* == poly_coeff0 ==. */ > > + .align 64 > > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > + /* == Half ==. */ > > + .align 64 > > + .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > > + /* == L2H = log(2)_high ==. */ > > + .align 64 > > + .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > > + /* == L2L = log(2)_low ==. */ > > + .align 64 > > + .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > > + .align 64 > > + .type __svml_satanh_data_internal_avx512, @object > > + .size __svml_satanh_data_internal_avx512, .-__svml_satanh_data_internal_avx512 > > -- > > 2.25.1 > >
Can you please also include Nested #ifdef example. Multiline comment example. Single line comment starts with #. Thank you so much. Sunil On Fri, Feb 4, 2022 at 11:46 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote: > > On Sat, Feb 5, 2022 at 2:01 AM Sunil Pandey <skpgkp2@gmail.com> wrote: > > > > Hi Noah, > > > > Since this patch is about glibc assembly language formatting, it may be > > helpful to everyone, if there is a section for glibc assembly coding > > in manual. > > > > https://sourceware.org/glibc/wiki/Style_and_Conventions > > > > You may also consider putting your tool in glibc code base, so that people > > can easily find/use it to check/format their assembly code. > > Like the idea. How does the following sound: > > == x86 GAS (Assembly) == > > The following are stylistic conventions for x86 GAS > contributions. Other style conventions that are relevant to x86 GAS > syntax are also included (i.e column limit, indenting preprocessor > directives, etc..). > > 1. Instructions should be proceeded by a tab. > 2. Instruction less than 8 characters in length should have a tab > between it and the first operand. > 3. Instruction greater than 7 characters in length should have a > space between it and the first operand. > 4. There should be a space after the comma seperating operands. > For example for rules 1, 2, 3, and 4: > ``` > /* <tab><short instruction><tab><op0><comma><space><op1>. */ > addl $1, %eax > /* <tab><long instruction><space><op0><comma><space><op1>. */ > vpmovmaskb %ymm0, %eax > ``` > > 5. Comments should be indented with code: > For example for rule 5: > ``` > /* Function XYZ returns. */ > ENTRY(XYZ) > /* Return from XYZ. */ > ret > END(XYZ) > ``` > > 6. Tab after `#define`d names and their value. > For example: > ``` > /* No value for 'HELLO' so no tab afterwards. */ > #define HELLO > > /* Value for 'WORLD' so tab separated 'WORLD' from '10'. */ > #define WORLD 10 > ``` > > > > > > https://github.com/goldsteinn/assembly-beautifier > > Thats not an official tool. Its code quality is not really up to standard > and I can't really commit to maintaining it. > > If its improved to a state where its good enough for GLIBC I'll > post a patch. > > > > Thank, > > Sunil > > > > On Thu, Feb 3, 2022 at 2:00 PM Noah Goldstein via Libc-alpha > > <libc-alpha@sourceware.org> wrote: > > > > > > Reformats to match style of other hand coded assembly files. > > > > > > The changes are: > > > 1. Replace 8x space with tab before instructions. > > > 2. After instruction len < 8 use tab. > > > 3. After instruction len >= 8 use space. > > > 4. 1 Space after comma between instruction operands. > > > 5. Indent comments similiar with code. > > > 6. Make comments complete sentences. > > > 7. Tab after '#define' > > > 8. Spaces at '#' representing the depth. > > > > > > The final executable is unchanged by this commit. > > > --- > > > The changes for this patch where made with the following > > > script: https://github.com/goldsteinn/assembly-beautifier > > > > > > The goal of this patch is just to reformat the code > > > so it is more human friendly and try create a style > > > that future patches will be based on. > > > > > > If this patch is accepted ensuing patches to > > > optimize the performance of svml_s_atanhf16_core_avx512.S > > > will be based on this patch. > > > > > > .../multiarch/svml_s_atanhf16_core_avx512.S | 655 +++++++++--------- > > > 1 file changed, 321 insertions(+), 334 deletions(-) > > > > > > diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > > index f863f4f959..ed90a427a6 100644 > > > --- a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > > +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > > @@ -33,361 +33,348 @@ > > > > > > /* Offsets for data table __svml_satanh_data_internal_avx512 > > > */ > > > -#define Log_tbl_H 0 > > > -#define Log_tbl_L 128 > > > -#define One 256 > > > -#define AbsMask 320 > > > -#define AddB5 384 > > > -#define RcpBitMask 448 > > > -#define poly_coeff3 512 > > > -#define poly_coeff2 576 > > > -#define poly_coeff1 640 > > > -#define poly_coeff0 704 > > > -#define Half 768 > > > -#define L2H 832 > > > -#define L2L 896 > > > +#define Log_tbl_H 0 > > > +#define Log_tbl_L 128 > > > +#define One 256 > > > +#define AbsMask 320 > > > +#define AddB5 384 > > > +#define RcpBitMask 448 > > > +#define poly_coeff3 512 > > > +#define poly_coeff2 576 > > > +#define poly_coeff1 640 > > > +#define poly_coeff0 704 > > > +#define Half 768 > > > +#define L2H 832 > > > +#define L2L 896 > > > > > > #include <sysdep.h> > > > > > > - .text > > > - .section .text.exex512,"ax",@progbits > > > + .text > > > + .section .text.exex512, "ax", @progbits > > > ENTRY(_ZGVeN16v_atanhf_skx) > > > - pushq %rbp > > > - cfi_def_cfa_offset(16) > > > - movq %rsp, %rbp > > > - cfi_def_cfa(6, 16) > > > - cfi_offset(6, -16) > > > - andq $-64, %rsp > > > - subq $192, %rsp > > > - vmovups One+__svml_satanh_data_internal_avx512(%rip), %zmm4 > > > - > > > -/* round reciprocals to 1+5b mantissas */ > > > - vmovups AddB5+__svml_satanh_data_internal_avx512(%rip), %zmm14 > > > - vmovups RcpBitMask+__svml_satanh_data_internal_avx512(%rip), %zmm1 > > > - vmovaps %zmm0, %zmm11 > > > - vandps AbsMask+__svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > > > - > > > -/* 1+y */ > > > - vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > > > - > > > -/* 1-y */ > > > - vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > > > - vxorps %zmm6, %zmm11, %zmm10 > > > - > > > -/* Yp_high */ > > > - vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > > > - > > > -/* -Ym_high */ > > > - vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > > > - > > > -/* RcpP ~ 1/Yp */ > > > - vrcp14ps %zmm9, %zmm12 > > > - > > > -/* RcpM ~ 1/Ym */ > > > - vrcp14ps %zmm8, %zmm13 > > > - > > > -/* input outside (-1, 1) ? */ > > > - vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > > > - vpaddd %zmm14, %zmm12, %zmm15 > > > - vpaddd %zmm14, %zmm13, %zmm0 > > > - > > > -/* Yp_low */ > > > - vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > > > - vandps %zmm1, %zmm15, %zmm7 > > > - vandps %zmm1, %zmm0, %zmm12 > > > - > > > -/* Ym_low */ > > > - vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > > > - > > > -/* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low */ > > > - vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > > > - > > > -/* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low */ > > > - vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > > > - vmovups Log_tbl_L+__svml_satanh_data_internal_avx512(%rip), %zmm8 > > > - vmovups Log_tbl_L+64+__svml_satanh_data_internal_avx512(%rip), %zmm13 > > > - > > > -/* exponents */ > > > - vgetexpps {sae}, %zmm7, %zmm15 > > > - vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > > > - > > > -/* Table lookups */ > > > - vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > > > - vgetexpps {sae}, %zmm12, %zmm14 > > > - vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > > > - > > > -/* Prepare table index */ > > > - vpsrld $18, %zmm7, %zmm3 > > > - vpsrld $18, %zmm12, %zmm2 > > > - vmovups Log_tbl_H+64+__svml_satanh_data_internal_avx512(%rip), %zmm7 > > > - vmovups poly_coeff1+__svml_satanh_data_internal_avx512(%rip), %zmm12 > > > - > > > -/* Km-Kp */ > > > - vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > > > - kmovw %k0, %edx > > > - vmovaps %zmm3, %zmm0 > > > - vpermi2ps %zmm13, %zmm8, %zmm3 > > > - vpermt2ps %zmm13, %zmm2, %zmm8 > > > - vpermi2ps %zmm7, %zmm6, %zmm0 > > > - vpermt2ps %zmm7, %zmm2, %zmm6 > > > - vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > > > - > > > -/* K*L2H + Th */ > > > - vmovups L2H+__svml_satanh_data_internal_avx512(%rip), %zmm2 > > > - > > > -/* K*L2L + Tl */ > > > - vmovups L2L+__svml_satanh_data_internal_avx512(%rip), %zmm3 > > > - > > > -/* polynomials */ > > > - vmovups poly_coeff3+__svml_satanh_data_internal_avx512(%rip), %zmm7 > > > - vmovups poly_coeff0+__svml_satanh_data_internal_avx512(%rip), %zmm13 > > > - > > > -/* table values */ > > > - vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > > > - vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > > > - vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > > > - vmovups poly_coeff2+__svml_satanh_data_internal_avx512(%rip), %zmm3 > > > - vmovaps %zmm3, %zmm2 > > > - vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > > > - vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > > > - vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > > > - vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > > > - vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > > > - vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > > > - > > > -/* (K*L2L + Tl) + Rp*PolyP */ > > > - vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > > > - vorps Half+__svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > > > - > > > -/* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM */ > > > - vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > > > - vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > > > - vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > > > - testl %edx, %edx > > > - > > > -/* Go to special inputs processing branch */ > > > - jne L(SPECIAL_VALUES_BRANCH) > > > - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm11 > > > - > > > -/* Restore registers > > > - * and exit the function > > > - */ > > > + pushq %rbp > > > + cfi_def_cfa_offset (16) > > > + movq %rsp, %rbp > > > + cfi_def_cfa (6, 16) > > > + cfi_offset (6, -16) > > > + andq $-64, %rsp > > > + subq $192, %rsp > > > + vmovups One + __svml_satanh_data_internal_avx512(%rip), %zmm4 > > > + > > > + /* round reciprocals to 1+5b mantissas. */ > > > + vmovups AddB5 + __svml_satanh_data_internal_avx512(%rip), %zmm14 > > > + vmovups RcpBitMask + __svml_satanh_data_internal_avx512(%rip), %zmm1 > > > + vmovaps %zmm0, %zmm11 > > > + vandps AbsMask + __svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > > > + > > > + /* 1+y. */ > > > + vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > > > + > > > + /* 1-y. */ > > > + vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > > > + vxorps %zmm6, %zmm11, %zmm10 > > > + > > > + /* Yp_high. */ > > > + vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > > > + > > > + /* -Ym_high. */ > > > + vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > > > + > > > + /* RcpP ~ 1/Yp. */ > > > + vrcp14ps %zmm9, %zmm12 > > > + > > > + /* RcpM ~ 1/Ym. */ > > > + vrcp14ps %zmm8, %zmm13 > > > + > > > + /* input outside (-1, 1) ?. */ > > > + vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > > > + vpaddd %zmm14, %zmm12, %zmm15 > > > + vpaddd %zmm14, %zmm13, %zmm0 > > > + > > > + /* Yp_low. */ > > > + vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > > > + vandps %zmm1, %zmm15, %zmm7 > > > + vandps %zmm1, %zmm0, %zmm12 > > > + > > > + /* Ym_low. */ > > > + vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > > > + > > > + /* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low. */ > > > + vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > > > + > > > + /* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low. */ > > > + vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > > > + vmovups Log_tbl_L + __svml_satanh_data_internal_avx512(%rip), %zmm8 > > > + vmovups Log_tbl_L + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > > > + > > > + /* exponents. */ > > > + vgetexpps {sae}, %zmm7, %zmm15 > > > + vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > > > + > > > + /* Table lookups. */ > > > + vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > > > + vgetexpps {sae}, %zmm12, %zmm14 > > > + vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > > > + > > > + /* Prepare table index. */ > > > + vpsrld $18, %zmm7, %zmm3 > > > + vpsrld $18, %zmm12, %zmm2 > > > + vmovups Log_tbl_H + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > > > + vmovups poly_coeff1 + __svml_satanh_data_internal_avx512(%rip), %zmm12 > > > + > > > + /* Km-Kp. */ > > > + vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > > > + kmovw %k0, %edx > > > + vmovaps %zmm3, %zmm0 > > > + vpermi2ps %zmm13, %zmm8, %zmm3 > > > + vpermt2ps %zmm13, %zmm2, %zmm8 > > > + vpermi2ps %zmm7, %zmm6, %zmm0 > > > + vpermt2ps %zmm7, %zmm2, %zmm6 > > > + vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > > > + > > > + /* K*L2H + Th. */ > > > + vmovups L2H + __svml_satanh_data_internal_avx512(%rip), %zmm2 > > > + > > > + /* K*L2L + Tl. */ > > > + vmovups L2L + __svml_satanh_data_internal_avx512(%rip), %zmm3 > > > + > > > + /* polynomials. */ > > > + vmovups poly_coeff3 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > > > + vmovups poly_coeff0 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > > > + > > > + /* table values. */ > > > + vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > > > + vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > > > + vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > > > + vmovups poly_coeff2 + __svml_satanh_data_internal_avx512(%rip), %zmm3 > > > + vmovaps %zmm3, %zmm2 > > > + vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > > > + vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > > > + vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > > > + vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > > > + vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > > > + vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > > > + > > > + /* (K*L2L + Tl) + Rp*PolyP. */ > > > + vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > > > + vorps Half + __svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > > > + > > > + /* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM. */ > > > + vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > > > + vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > > > + vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > > > + testl %edx, %edx > > > + > > > + /* Go to special inputs processing branch. */ > > > + jne L(SPECIAL_VALUES_BRANCH) > > > + > > > + /* Restore registers * and exit the function. */ > > > > > > L(EXIT): > > > - movq %rbp, %rsp > > > - popq %rbp > > > - cfi_def_cfa(7, 8) > > > - cfi_restore(6) > > > - ret > > > - cfi_def_cfa(6, 16) > > > - cfi_offset(6, -16) > > > - > > > -/* Branch to process > > > - * special inputs > > > - */ > > > + movq %rbp, %rsp > > > + popq %rbp > > > + cfi_def_cfa (7, 8) > > > + cfi_restore (6) > > > + ret > > > + cfi_def_cfa (6, 16) > > > + cfi_offset (6, -16) > > > + > > > + /* Branch to process special inputs. */ > > > > > > L(SPECIAL_VALUES_BRANCH): > > > - vmovups %zmm11, 64(%rsp) > > > - vmovups %zmm0, 128(%rsp) > > > - # LOE rbx r12 r13 r14 r15 edx zmm0 > > > - > > > - xorl %eax, %eax > > > - # LOE rbx r12 r13 r14 r15 eax edx > > > - > > > - vzeroupper > > > - movq %r12, 16(%rsp) > > > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > > > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > > > - movl %eax, %r12d > > > - movq %r13, 8(%rsp) > > > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > > > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > > > - movl %edx, %r13d > > > - movq %r14, (%rsp) > > > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > > > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > > > - # LOE rbx r15 r12d r13d > > > - > > > -/* Range mask > > > - * bits check > > > - */ > > > + vmovups %zmm11, 64(%rsp) > > > + vmovups %zmm0, 128(%rsp) > > > + > > > + xorl %eax, %eax > > > + > > > + vzeroupper > > > + movq %r12, 16(%rsp) > > > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > > > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > > > + movl %eax, %r12d > > > + movq %r13, 8(%rsp) > > > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > > > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > > > + movl %edx, %r13d > > > + movq %r14, (%rsp) > > > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > > > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > > > + > > > + /* Range mask * bits check. */ > > > > > > L(RANGEMASK_CHECK): > > > - btl %r12d, %r13d > > > + btl %r12d, %r13d > > > > > > -/* Call scalar math function */ > > > - jc L(SCALAR_MATH_CALL) > > > - # LOE rbx r15 r12d r13d > > > + /* Call scalar math function. */ > > > + jc L(SCALAR_MATH_CALL) > > > > > > -/* Special inputs > > > - * processing loop > > > - */ > > > + /* Special inputs processing loop. */ > > > > > > L(SPECIAL_VALUES_LOOP): > > > - incl %r12d > > > - cmpl $16, %r12d > > > - > > > -/* Check bits in range mask */ > > > - jl L(RANGEMASK_CHECK) > > > - # LOE rbx r15 r12d r13d > > > - > > > - movq 16(%rsp), %r12 > > > - cfi_restore(12) > > > - movq 8(%rsp), %r13 > > > - cfi_restore(13) > > > - movq (%rsp), %r14 > > > - cfi_restore(14) > > > - vmovups 128(%rsp), %zmm0 > > > - > > > -/* Go to exit */ > > > - jmp L(EXIT) > > > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > > > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > > > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > > > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > > > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > > > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > > > - # LOE rbx r12 r13 r14 r15 zmm0 > > > - > > > -/* Scalar math fucntion call > > > - * to process special input > > > - */ > > > + incl %r12d > > > + cmpl $16, %r12d > > > + > > > + /* Check bits in range mask. */ > > > + jl L(RANGEMASK_CHECK) > > > + > > > + movq 16(%rsp), %r12 > > > + cfi_restore (12) > > > + movq 8(%rsp), %r13 > > > + cfi_restore (13) > > > + movq (%rsp), %r14 > > > + cfi_restore (14) > > > + vmovups 128(%rsp), %zmm0 > > > + > > > + /* Go to exit. */ > > > + jmp L(EXIT) > > > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > > > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > > > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > > > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > > > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > > > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > > > + > > > + /* Scalar math fucntion call to process special input. */ > > > > > > L(SCALAR_MATH_CALL): > > > - movl %r12d, %r14d > > > - movss 64(%rsp,%r14,4), %xmm0 > > > - call atanhf@PLT > > > - # LOE rbx r14 r15 r12d r13d xmm0 > > > + movl %r12d, %r14d > > > + movss 64(%rsp, %r14, 4), %xmm0 > > > + call atanhf@PLT > > > > > > - movss %xmm0, 128(%rsp,%r14,4) > > > + movss %xmm0, 128(%rsp, %r14, 4) > > > > > > -/* Process special inputs in loop */ > > > - jmp L(SPECIAL_VALUES_LOOP) > > > - # LOE rbx r15 r12d r13d > > > + /* Process special inputs in loop. */ > > > + jmp L(SPECIAL_VALUES_LOOP) > > > END(_ZGVeN16v_atanhf_skx) > > > > > > - .section .rodata, "a" > > > - .align 64 > > > + .section .rodata, "a" > > > + .align 64 > > > > > > #ifdef __svml_satanh_data_internal_avx512_typedef > > > -typedef unsigned int VUINT32; > > > -typedef struct { > > > - __declspec(align(64)) VUINT32 Log_tbl_H[32][1]; > > > - __declspec(align(64)) VUINT32 Log_tbl_L[32][1]; > > > - __declspec(align(64)) VUINT32 One[16][1]; > > > - __declspec(align(64)) VUINT32 AbsMask[16][1]; > > > - __declspec(align(64)) VUINT32 AddB5[16][1]; > > > - __declspec(align(64)) VUINT32 RcpBitMask[16][1]; > > > - __declspec(align(64)) VUINT32 poly_coeff3[16][1]; > > > - __declspec(align(64)) VUINT32 poly_coeff2[16][1]; > > > - __declspec(align(64)) VUINT32 poly_coeff1[16][1]; > > > - __declspec(align(64)) VUINT32 poly_coeff0[16][1]; > > > - __declspec(align(64)) VUINT32 Half[16][1]; > > > - __declspec(align(64)) VUINT32 L2H[16][1]; > > > - __declspec(align(64)) VUINT32 L2L[16][1]; > > > - } __svml_satanh_data_internal_avx512; > > > + typedef unsigned int VUINT32; > > > + typedef struct{ > > > + __declspec (align(64))VUINT32 Log_tbl_H[32][1]; > > > + __declspec (align(64))VUINT32 Log_tbl_L[32][1]; > > > + __declspec (align(64))VUINT32 One[16][1]; > > > + __declspec (align(64))VUINT32 AbsMask[16][1]; > > > + __declspec (align(64))VUINT32 AddB5[16][1]; > > > + __declspec (align(64))VUINT32 RcpBitMask[16][1]; > > > + __declspec (align(64))VUINT32 poly_coeff3[16][1]; > > > + __declspec (align(64))VUINT32 poly_coeff2[16][1]; > > > + __declspec (align(64))VUINT32 poly_coeff1[16][1]; > > > + __declspec (align(64))VUINT32 poly_coeff0[16][1]; > > > + __declspec (align(64))VUINT32 Half[16][1]; > > > + __declspec (align(64))VUINT32 L2H[16][1]; > > > + __declspec (align(64))VUINT32 L2L[16][1]; > > > + }__svml_satanh_data_internal_avx512; > > > #endif > > > __svml_satanh_data_internal_avx512: > > > - /*== Log_tbl_H ==*/ > > > - .long 0x00000000 > > > - .long 0x3cfc0000 > > > - .long 0x3d780000 > > > - .long 0x3db78000 > > > - .long 0x3df10000 > > > - .long 0x3e14c000 > > > - .long 0x3e300000 > > > - .long 0x3e4a8000 > > > - .long 0x3e648000 > > > - .long 0x3e7dc000 > > > - .long 0x3e8b4000 > > > - .long 0x3e974000 > > > - .long 0x3ea30000 > > > - .long 0x3eae8000 > > > - .long 0x3eb9c000 > > > - .long 0x3ec4e000 > > > - .long 0x3ecfa000 > > > - .long 0x3eda2000 > > > - .long 0x3ee48000 > > > - .long 0x3eeea000 > > > - .long 0x3ef8a000 > > > - .long 0x3f013000 > > > - .long 0x3f05f000 > > > - .long 0x3f0aa000 > > > - .long 0x3f0f4000 > > > - .long 0x3f13d000 > > > - .long 0x3f184000 > > > - .long 0x3f1ca000 > > > - .long 0x3f20f000 > > > - .long 0x3f252000 > > > - .long 0x3f295000 > > > - .long 0x3f2d7000 > > > - /*== Log_tbl_L ==*/ > > > - .align 64 > > > - .long 0x00000000 > > > - .long 0x3726c39e > > > - .long 0x38a30c01 > > > - .long 0x37528ae5 > > > - .long 0x38e0edc5 > > > - .long 0xb8ab41f8 > > > - .long 0xb7cf8f58 > > > - .long 0x3896a73d > > > - .long 0xb5838656 > > > - .long 0x380c36af > > > - .long 0xb8235454 > > > - .long 0x3862bae1 > > > - .long 0x38c5e10e > > > - .long 0x38dedfac > > > - .long 0x38ebfb5e > > > - .long 0xb8e63c9f > > > - .long 0xb85c1340 > > > - .long 0x38777bcd > > > - .long 0xb6038656 > > > - .long 0x37d40984 > > > - .long 0xb8b85028 > > > - .long 0xb8ad5a5a > > > - .long 0x3865c84a > > > - .long 0x38c3d2f5 > > > - .long 0x383ebce1 > > > - .long 0xb8a1ed76 > > > - .long 0xb7a332c4 > > > - .long 0xb779654f > > > - .long 0xb8602f73 > > > - .long 0x38f85db0 > > > - .long 0x37b4996f > > > - .long 0xb8bfb3ca > > > - /*== One ==*/ > > > - .align 64 > > > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > - /*== AbsMask ==*/ > > > - .align 64 > > > - .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > > > - /*== AddB5 ==*/ > > > - .align 64 > > > - .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > > > - /*== RcpBitMask ==*/ > > > - .align 64 > > > - .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > > > - /*== poly_coeff3 ==*/ > > > - .align 64 > > > - .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > > > - /*== poly_coeff2 ==*/ > > > - .align 64 > > > - .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > > > - /*== poly_coeff1 ==*/ > > > - .align 64 > > > - .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > > > - /*== poly_coeff0 ==*/ > > > - .align 64 > > > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > - /*== Half ==*/ > > > - .align 64 > > > - .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > > > - /*== L2H = log(2)_high ==*/ > > > - .align 64 > > > - .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > > > - /*== L2L = log(2)_low ==*/ > > > - .align 64 > > > - .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > > > - .align 64 > > > - .type __svml_satanh_data_internal_avx512,@object > > > - .size __svml_satanh_data_internal_avx512,.-__svml_satanh_data_internal_avx512 > > > + /* == Log_tbl_H ==. */ > > > + .long 0x00000000 > > > + .long 0x3cfc0000 > > > + .long 0x3d780000 > > > + .long 0x3db78000 > > > + .long 0x3df10000 > > > + .long 0x3e14c000 > > > + .long 0x3e300000 > > > + .long 0x3e4a8000 > > > + .long 0x3e648000 > > > + .long 0x3e7dc000 > > > + .long 0x3e8b4000 > > > + .long 0x3e974000 > > > + .long 0x3ea30000 > > > + .long 0x3eae8000 > > > + .long 0x3eb9c000 > > > + .long 0x3ec4e000 > > > + .long 0x3ecfa000 > > > + .long 0x3eda2000 > > > + .long 0x3ee48000 > > > + .long 0x3eeea000 > > > + .long 0x3ef8a000 > > > + .long 0x3f013000 > > > + .long 0x3f05f000 > > > + .long 0x3f0aa000 > > > + .long 0x3f0f4000 > > > + .long 0x3f13d000 > > > + .long 0x3f184000 > > > + .long 0x3f1ca000 > > > + .long 0x3f20f000 > > > + .long 0x3f252000 > > > + .long 0x3f295000 > > > + .long 0x3f2d7000 > > > + /* == Log_tbl_L ==. */ > > > + .align 64 > > > + .long 0x00000000 > > > + .long 0x3726c39e > > > + .long 0x38a30c01 > > > + .long 0x37528ae5 > > > + .long 0x38e0edc5 > > > + .long 0xb8ab41f8 > > > + .long 0xb7cf8f58 > > > + .long 0x3896a73d > > > + .long 0xb5838656 > > > + .long 0x380c36af > > > + .long 0xb8235454 > > > + .long 0x3862bae1 > > > + .long 0x38c5e10e > > > + .long 0x38dedfac > > > + .long 0x38ebfb5e > > > + .long 0xb8e63c9f > > > + .long 0xb85c1340 > > > + .long 0x38777bcd > > > + .long 0xb6038656 > > > + .long 0x37d40984 > > > + .long 0xb8b85028 > > > + .long 0xb8ad5a5a > > > + .long 0x3865c84a > > > + .long 0x38c3d2f5 > > > + .long 0x383ebce1 > > > + .long 0xb8a1ed76 > > > + .long 0xb7a332c4 > > > + .long 0xb779654f > > > + .long 0xb8602f73 > > > + .long 0x38f85db0 > > > + .long 0x37b4996f > > > + .long 0xb8bfb3ca > > > + /* == One ==. */ > > > + .align 64 > > > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > + /* == AbsMask ==. */ > > > + .align 64 > > > + .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > > > + /* == AddB5 ==. */ > > > + .align 64 > > > + .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > > > + /* == RcpBitMask ==. */ > > > + .align 64 > > > + .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > > > + /* == poly_coeff3 ==. */ > > > + .align 64 > > > + .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > > > + /* == poly_coeff2 ==. */ > > > + .align 64 > > > + .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > > > + /* == poly_coeff1 ==. */ > > > + .align 64 > > > + .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > > > + /* == poly_coeff0 ==. */ > > > + .align 64 > > > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > + /* == Half ==. */ > > > + .align 64 > > > + .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > > > + /* == L2H = log(2)_high ==. */ > > > + .align 64 > > > + .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > > > + /* == L2L = log(2)_low ==. */ > > > + .align 64 > > > + .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > > > + .align 64 > > > + .type __svml_satanh_data_internal_avx512, @object > > > + .size __svml_satanh_data_internal_avx512, .-__svml_satanh_data_internal_avx512 > > > -- > > > 2.25.1 > > >
On Mon, Feb 7, 2022 at 7:21 AM Sunil Pandey <skpgkp2@gmail.com> wrote: > > Can you please also include > > Nested #ifdef example. > Multiline comment example. > Single line comment starts with #. V2 (note gmail is eating the tabs, but the examples where I mention them will have them when posted on the wiki). == x86 GAS (Assembly) == The following are stylistic conventions for x86 GAS contributions. Other style conventions that are relevant to x86 GAS syntax are also included (for example [[https://sourceware.org/glibc/wiki/Style_and_Conventions#A79-Column_Lines|Column Limit of 79]] and [[https://sourceware.org/glibc/wiki/Style_and_Conventions#Nested_C_Preprocessor_Directives|Nested Preprocessor Directives]] 1. Instructions should be proceeded by a tab. 2. Instruction less than 8 characters in length should have a tab between it and the first operand. 3. Instruction greater than 7 characters in length should have a space between it and the first operand. 4. There should be a space after the comma seperating operands. For example for rules 1, 2, 3, and 4: ``` /* <tab><short instruction><tab><op0><comma><space><op1>. */ addl $1, %eax /* <tab><long instruction><space><op0><comma><space><op1>. */ vpmovmaskb %ymm0, %eax ``` 5. Comments should be indented with code: For example for rule 5: ``` /* Function XYZ returns. */ ENTRY(XYZ) /* Return from XYZ. */ ret END(XYZ) ``` 6. Tab after `#define`d names and their value. For example: ``` /* No value for 'HELLO' so no tab afterwards. */ #define HELLO /* Value for 'WORLD' so tab separated 'WORLD' from '10'. */ #define WORLD 10 ``` 7. Use C-Style comments. 8. Comments should be filled to obey the 79 character column limit. For example: ``` /* Bad: This comment is going to go beyond the 79 character column limit but be on one line. */ /* Good: This comment is going to go beyond the 79 character column limit but be on one line. */ ``` > > Thank you so much. > Sunil > > On Fri, Feb 4, 2022 at 11:46 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote: > > > > On Sat, Feb 5, 2022 at 2:01 AM Sunil Pandey <skpgkp2@gmail.com> wrote: > > > > > > Hi Noah, > > > > > > Since this patch is about glibc assembly language formatting, it may be > > > helpful to everyone, if there is a section for glibc assembly coding > > > in manual. > > > > > > https://sourceware.org/glibc/wiki/Style_and_Conventions > > > > > > You may also consider putting your tool in glibc code base, so that people > > > can easily find/use it to check/format their assembly code. > > > > Like the idea. How does the following sound: > > > > == x86 GAS (Assembly) == > > > > The following are stylistic conventions for x86 GAS > > contributions. Other style conventions that are relevant to x86 GAS > > syntax are also included (i.e column limit, indenting preprocessor > > directives, etc..). > > > > 1. Instructions should be proceeded by a tab. > > 2. Instruction less than 8 characters in length should have a tab > > between it and the first operand. > > 3. Instruction greater than 7 characters in length should have a > > space between it and the first operand. > > 4. There should be a space after the comma seperating operands. > > For example for rules 1, 2, 3, and 4: > > ``` > > /* <tab><short instruction><tab><op0><comma><space><op1>. */ > > addl $1, %eax > > /* <tab><long instruction><space><op0><comma><space><op1>. */ > > vpmovmaskb %ymm0, %eax > > ``` > > > > 5. Comments should be indented with code: > > For example for rule 5: > > ``` > > /* Function XYZ returns. */ > > ENTRY(XYZ) > > /* Return from XYZ. */ > > ret > > END(XYZ) > > ``` > > > > 6. Tab after `#define`d names and their value. > > For example: > > ``` > > /* No value for 'HELLO' so no tab afterwards. */ > > #define HELLO > > > > /* Value for 'WORLD' so tab separated 'WORLD' from '10'. */ > > #define WORLD 10 > > ``` > > > > > > > > > > https://github.com/goldsteinn/assembly-beautifier > > > > Thats not an official tool. Its code quality is not really up to standard > > and I can't really commit to maintaining it. > > > > If its improved to a state where its good enough for GLIBC I'll > > post a patch. > > > > > > Thank, > > > Sunil > > > > > > On Thu, Feb 3, 2022 at 2:00 PM Noah Goldstein via Libc-alpha > > > <libc-alpha@sourceware.org> wrote: > > > > > > > > Reformats to match style of other hand coded assembly files. > > > > > > > > The changes are: > > > > 1. Replace 8x space with tab before instructions. > > > > 2. After instruction len < 8 use tab. > > > > 3. After instruction len >= 8 use space. > > > > 4. 1 Space after comma between instruction operands. > > > > 5. Indent comments similiar with code. > > > > 6. Make comments complete sentences. > > > > 7. Tab after '#define' > > > > 8. Spaces at '#' representing the depth. > > > > > > > > The final executable is unchanged by this commit. > > > > --- > > > > The changes for this patch where made with the following > > > > script: https://github.com/goldsteinn/assembly-beautifier > > > > > > > > The goal of this patch is just to reformat the code > > > > so it is more human friendly and try create a style > > > > that future patches will be based on. > > > > > > > > If this patch is accepted ensuing patches to > > > > optimize the performance of svml_s_atanhf16_core_avx512.S > > > > will be based on this patch. > > > > > > > > .../multiarch/svml_s_atanhf16_core_avx512.S | 655 +++++++++--------- > > > > 1 file changed, 321 insertions(+), 334 deletions(-) > > > > > > > > diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > > > index f863f4f959..ed90a427a6 100644 > > > > --- a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > > > +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S > > > > @@ -33,361 +33,348 @@ > > > > > > > > /* Offsets for data table __svml_satanh_data_internal_avx512 > > > > */ > > > > -#define Log_tbl_H 0 > > > > -#define Log_tbl_L 128 > > > > -#define One 256 > > > > -#define AbsMask 320 > > > > -#define AddB5 384 > > > > -#define RcpBitMask 448 > > > > -#define poly_coeff3 512 > > > > -#define poly_coeff2 576 > > > > -#define poly_coeff1 640 > > > > -#define poly_coeff0 704 > > > > -#define Half 768 > > > > -#define L2H 832 > > > > -#define L2L 896 > > > > +#define Log_tbl_H 0 > > > > +#define Log_tbl_L 128 > > > > +#define One 256 > > > > +#define AbsMask 320 > > > > +#define AddB5 384 > > > > +#define RcpBitMask 448 > > > > +#define poly_coeff3 512 > > > > +#define poly_coeff2 576 > > > > +#define poly_coeff1 640 > > > > +#define poly_coeff0 704 > > > > +#define Half 768 > > > > +#define L2H 832 > > > > +#define L2L 896 > > > > > > > > #include <sysdep.h> > > > > > > > > - .text > > > > - .section .text.exex512,"ax",@progbits > > > > + .text > > > > + .section .text.exex512, "ax", @progbits > > > > ENTRY(_ZGVeN16v_atanhf_skx) > > > > - pushq %rbp > > > > - cfi_def_cfa_offset(16) > > > > - movq %rsp, %rbp > > > > - cfi_def_cfa(6, 16) > > > > - cfi_offset(6, -16) > > > > - andq $-64, %rsp > > > > - subq $192, %rsp > > > > - vmovups One+__svml_satanh_data_internal_avx512(%rip), %zmm4 > > > > - > > > > -/* round reciprocals to 1+5b mantissas */ > > > > - vmovups AddB5+__svml_satanh_data_internal_avx512(%rip), %zmm14 > > > > - vmovups RcpBitMask+__svml_satanh_data_internal_avx512(%rip), %zmm1 > > > > - vmovaps %zmm0, %zmm11 > > > > - vandps AbsMask+__svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > > > > - > > > > -/* 1+y */ > > > > - vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > > > > - > > > > -/* 1-y */ > > > > - vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > > > > - vxorps %zmm6, %zmm11, %zmm10 > > > > - > > > > -/* Yp_high */ > > > > - vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > > > > - > > > > -/* -Ym_high */ > > > > - vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > > > > - > > > > -/* RcpP ~ 1/Yp */ > > > > - vrcp14ps %zmm9, %zmm12 > > > > - > > > > -/* RcpM ~ 1/Ym */ > > > > - vrcp14ps %zmm8, %zmm13 > > > > - > > > > -/* input outside (-1, 1) ? */ > > > > - vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > > > > - vpaddd %zmm14, %zmm12, %zmm15 > > > > - vpaddd %zmm14, %zmm13, %zmm0 > > > > - > > > > -/* Yp_low */ > > > > - vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > > > > - vandps %zmm1, %zmm15, %zmm7 > > > > - vandps %zmm1, %zmm0, %zmm12 > > > > - > > > > -/* Ym_low */ > > > > - vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > > > > - > > > > -/* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low */ > > > > - vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > > > > - > > > > -/* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low */ > > > > - vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > > > > - vmovups Log_tbl_L+__svml_satanh_data_internal_avx512(%rip), %zmm8 > > > > - vmovups Log_tbl_L+64+__svml_satanh_data_internal_avx512(%rip), %zmm13 > > > > - > > > > -/* exponents */ > > > > - vgetexpps {sae}, %zmm7, %zmm15 > > > > - vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > > > > - > > > > -/* Table lookups */ > > > > - vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > > > > - vgetexpps {sae}, %zmm12, %zmm14 > > > > - vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > > > > - > > > > -/* Prepare table index */ > > > > - vpsrld $18, %zmm7, %zmm3 > > > > - vpsrld $18, %zmm12, %zmm2 > > > > - vmovups Log_tbl_H+64+__svml_satanh_data_internal_avx512(%rip), %zmm7 > > > > - vmovups poly_coeff1+__svml_satanh_data_internal_avx512(%rip), %zmm12 > > > > - > > > > -/* Km-Kp */ > > > > - vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > > > > - kmovw %k0, %edx > > > > - vmovaps %zmm3, %zmm0 > > > > - vpermi2ps %zmm13, %zmm8, %zmm3 > > > > - vpermt2ps %zmm13, %zmm2, %zmm8 > > > > - vpermi2ps %zmm7, %zmm6, %zmm0 > > > > - vpermt2ps %zmm7, %zmm2, %zmm6 > > > > - vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > > > > - > > > > -/* K*L2H + Th */ > > > > - vmovups L2H+__svml_satanh_data_internal_avx512(%rip), %zmm2 > > > > - > > > > -/* K*L2L + Tl */ > > > > - vmovups L2L+__svml_satanh_data_internal_avx512(%rip), %zmm3 > > > > - > > > > -/* polynomials */ > > > > - vmovups poly_coeff3+__svml_satanh_data_internal_avx512(%rip), %zmm7 > > > > - vmovups poly_coeff0+__svml_satanh_data_internal_avx512(%rip), %zmm13 > > > > - > > > > -/* table values */ > > > > - vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > > > > - vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > > > > - vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > > > > - vmovups poly_coeff2+__svml_satanh_data_internal_avx512(%rip), %zmm3 > > > > - vmovaps %zmm3, %zmm2 > > > > - vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > > > > - vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > > > > - vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > > > > - vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > > > > - vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > > > > - vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > > > > - > > > > -/* (K*L2L + Tl) + Rp*PolyP */ > > > > - vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > > > > - vorps Half+__svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > > > > - > > > > -/* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM */ > > > > - vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > > > > - vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > > > > - vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > > > > - testl %edx, %edx > > > > - > > > > -/* Go to special inputs processing branch */ > > > > - jne L(SPECIAL_VALUES_BRANCH) > > > > - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm11 > > > > - > > > > -/* Restore registers > > > > - * and exit the function > > > > - */ > > > > + pushq %rbp > > > > + cfi_def_cfa_offset (16) > > > > + movq %rsp, %rbp > > > > + cfi_def_cfa (6, 16) > > > > + cfi_offset (6, -16) > > > > + andq $-64, %rsp > > > > + subq $192, %rsp > > > > + vmovups One + __svml_satanh_data_internal_avx512(%rip), %zmm4 > > > > + > > > > + /* round reciprocals to 1+5b mantissas. */ > > > > + vmovups AddB5 + __svml_satanh_data_internal_avx512(%rip), %zmm14 > > > > + vmovups RcpBitMask + __svml_satanh_data_internal_avx512(%rip), %zmm1 > > > > + vmovaps %zmm0, %zmm11 > > > > + vandps AbsMask + __svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 > > > > + > > > > + /* 1+y. */ > > > > + vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 > > > > + > > > > + /* 1-y. */ > > > > + vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 > > > > + vxorps %zmm6, %zmm11, %zmm10 > > > > + > > > > + /* Yp_high. */ > > > > + vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 > > > > + > > > > + /* -Ym_high. */ > > > > + vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 > > > > + > > > > + /* RcpP ~ 1/Yp. */ > > > > + vrcp14ps %zmm9, %zmm12 > > > > + > > > > + /* RcpM ~ 1/Ym. */ > > > > + vrcp14ps %zmm8, %zmm13 > > > > + > > > > + /* input outside (-1, 1) ?. */ > > > > + vcmpps $21, {sae}, %zmm4, %zmm6, %k0 > > > > + vpaddd %zmm14, %zmm12, %zmm15 > > > > + vpaddd %zmm14, %zmm13, %zmm0 > > > > + > > > > + /* Yp_low. */ > > > > + vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 > > > > + vandps %zmm1, %zmm15, %zmm7 > > > > + vandps %zmm1, %zmm0, %zmm12 > > > > + > > > > + /* Ym_low. */ > > > > + vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 > > > > + > > > > + /* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low. */ > > > > + vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 > > > > + > > > > + /* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low. */ > > > > + vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 > > > > + vmovups Log_tbl_L + __svml_satanh_data_internal_avx512(%rip), %zmm8 > > > > + vmovups Log_tbl_L + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > > > > + > > > > + /* exponents. */ > > > > + vgetexpps {sae}, %zmm7, %zmm15 > > > > + vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 > > > > + > > > > + /* Table lookups. */ > > > > + vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 > > > > + vgetexpps {sae}, %zmm12, %zmm14 > > > > + vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 > > > > + > > > > + /* Prepare table index. */ > > > > + vpsrld $18, %zmm7, %zmm3 > > > > + vpsrld $18, %zmm12, %zmm2 > > > > + vmovups Log_tbl_H + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > > > > + vmovups poly_coeff1 + __svml_satanh_data_internal_avx512(%rip), %zmm12 > > > > + > > > > + /* Km-Kp. */ > > > > + vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 > > > > + kmovw %k0, %edx > > > > + vmovaps %zmm3, %zmm0 > > > > + vpermi2ps %zmm13, %zmm8, %zmm3 > > > > + vpermt2ps %zmm13, %zmm2, %zmm8 > > > > + vpermi2ps %zmm7, %zmm6, %zmm0 > > > > + vpermt2ps %zmm7, %zmm2, %zmm6 > > > > + vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 > > > > + > > > > + /* K*L2H + Th. */ > > > > + vmovups L2H + __svml_satanh_data_internal_avx512(%rip), %zmm2 > > > > + > > > > + /* K*L2L + Tl. */ > > > > + vmovups L2L + __svml_satanh_data_internal_avx512(%rip), %zmm3 > > > > + > > > > + /* polynomials. */ > > > > + vmovups poly_coeff3 + __svml_satanh_data_internal_avx512(%rip), %zmm7 > > > > + vmovups poly_coeff0 + __svml_satanh_data_internal_avx512(%rip), %zmm13 > > > > + > > > > + /* table values. */ > > > > + vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 > > > > + vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 > > > > + vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 > > > > + vmovups poly_coeff2 + __svml_satanh_data_internal_avx512(%rip), %zmm3 > > > > + vmovaps %zmm3, %zmm2 > > > > + vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 > > > > + vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 > > > > + vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 > > > > + vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 > > > > + vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 > > > > + vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 > > > > + > > > > + /* (K*L2L + Tl) + Rp*PolyP. */ > > > > + vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 > > > > + vorps Half + __svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 > > > > + > > > > + /* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM. */ > > > > + vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 > > > > + vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 > > > > + vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 > > > > + testl %edx, %edx > > > > + > > > > + /* Go to special inputs processing branch. */ > > > > + jne L(SPECIAL_VALUES_BRANCH) > > > > + > > > > + /* Restore registers * and exit the function. */ > > > > > > > > L(EXIT): > > > > - movq %rbp, %rsp > > > > - popq %rbp > > > > - cfi_def_cfa(7, 8) > > > > - cfi_restore(6) > > > > - ret > > > > - cfi_def_cfa(6, 16) > > > > - cfi_offset(6, -16) > > > > - > > > > -/* Branch to process > > > > - * special inputs > > > > - */ > > > > + movq %rbp, %rsp > > > > + popq %rbp > > > > + cfi_def_cfa (7, 8) > > > > + cfi_restore (6) > > > > + ret > > > > + cfi_def_cfa (6, 16) > > > > + cfi_offset (6, -16) > > > > + > > > > + /* Branch to process special inputs. */ > > > > > > > > L(SPECIAL_VALUES_BRANCH): > > > > - vmovups %zmm11, 64(%rsp) > > > > - vmovups %zmm0, 128(%rsp) > > > > - # LOE rbx r12 r13 r14 r15 edx zmm0 > > > > - > > > > - xorl %eax, %eax > > > > - # LOE rbx r12 r13 r14 r15 eax edx > > > > - > > > > - vzeroupper > > > > - movq %r12, 16(%rsp) > > > > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > > > > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > > > > - movl %eax, %r12d > > > > - movq %r13, 8(%rsp) > > > > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > > > > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > > > > - movl %edx, %r13d > > > > - movq %r14, (%rsp) > > > > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > > > > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > > > > - # LOE rbx r15 r12d r13d > > > > - > > > > -/* Range mask > > > > - * bits check > > > > - */ > > > > + vmovups %zmm11, 64(%rsp) > > > > + vmovups %zmm0, 128(%rsp) > > > > + > > > > + xorl %eax, %eax > > > > + > > > > + vzeroupper > > > > + movq %r12, 16(%rsp) > > > > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > > > > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > > > > + movl %eax, %r12d > > > > + movq %r13, 8(%rsp) > > > > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > > > > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > > > > + movl %edx, %r13d > > > > + movq %r14, (%rsp) > > > > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > > > > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > > > > + > > > > + /* Range mask * bits check. */ > > > > > > > > L(RANGEMASK_CHECK): > > > > - btl %r12d, %r13d > > > > + btl %r12d, %r13d > > > > > > > > -/* Call scalar math function */ > > > > - jc L(SCALAR_MATH_CALL) > > > > - # LOE rbx r15 r12d r13d > > > > + /* Call scalar math function. */ > > > > + jc L(SCALAR_MATH_CALL) > > > > > > > > -/* Special inputs > > > > - * processing loop > > > > - */ > > > > + /* Special inputs processing loop. */ > > > > > > > > L(SPECIAL_VALUES_LOOP): > > > > - incl %r12d > > > > - cmpl $16, %r12d > > > > - > > > > -/* Check bits in range mask */ > > > > - jl L(RANGEMASK_CHECK) > > > > - # LOE rbx r15 r12d r13d > > > > - > > > > - movq 16(%rsp), %r12 > > > > - cfi_restore(12) > > > > - movq 8(%rsp), %r13 > > > > - cfi_restore(13) > > > > - movq (%rsp), %r14 > > > > - cfi_restore(14) > > > > - vmovups 128(%rsp), %zmm0 > > > > - > > > > -/* Go to exit */ > > > > - jmp L(EXIT) > > > > - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ > > > > - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 > > > > - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ > > > > - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 > > > > - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ > > > > - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 > > > > - # LOE rbx r12 r13 r14 r15 zmm0 > > > > - > > > > -/* Scalar math fucntion call > > > > - * to process special input > > > > - */ > > > > + incl %r12d > > > > + cmpl $16, %r12d > > > > + > > > > + /* Check bits in range mask. */ > > > > + jl L(RANGEMASK_CHECK) > > > > + > > > > + movq 16(%rsp), %r12 > > > > + cfi_restore (12) > > > > + movq 8(%rsp), %r13 > > > > + cfi_restore (13) > > > > + movq (%rsp), %r14 > > > > + cfi_restore (14) > > > > + vmovups 128(%rsp), %zmm0 > > > > + > > > > + /* Go to exit. */ > > > > + jmp L(EXIT) > > > > + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > > + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ > > > > + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 > > > > + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > > + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ > > > > + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 > > > > + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: > > > > + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ > > > > + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 > > > > + > > > > + /* Scalar math fucntion call to process special input. */ > > > > > > > > L(SCALAR_MATH_CALL): > > > > - movl %r12d, %r14d > > > > - movss 64(%rsp,%r14,4), %xmm0 > > > > - call atanhf@PLT > > > > - # LOE rbx r14 r15 r12d r13d xmm0 > > > > + movl %r12d, %r14d > > > > + movss 64(%rsp, %r14, 4), %xmm0 > > > > + call atanhf@PLT > > > > > > > > - movss %xmm0, 128(%rsp,%r14,4) > > > > + movss %xmm0, 128(%rsp, %r14, 4) > > > > > > > > -/* Process special inputs in loop */ > > > > - jmp L(SPECIAL_VALUES_LOOP) > > > > - # LOE rbx r15 r12d r13d > > > > + /* Process special inputs in loop. */ > > > > + jmp L(SPECIAL_VALUES_LOOP) > > > > END(_ZGVeN16v_atanhf_skx) > > > > > > > > - .section .rodata, "a" > > > > - .align 64 > > > > + .section .rodata, "a" > > > > + .align 64 > > > > > > > > #ifdef __svml_satanh_data_internal_avx512_typedef > > > > -typedef unsigned int VUINT32; > > > > -typedef struct { > > > > - __declspec(align(64)) VUINT32 Log_tbl_H[32][1]; > > > > - __declspec(align(64)) VUINT32 Log_tbl_L[32][1]; > > > > - __declspec(align(64)) VUINT32 One[16][1]; > > > > - __declspec(align(64)) VUINT32 AbsMask[16][1]; > > > > - __declspec(align(64)) VUINT32 AddB5[16][1]; > > > > - __declspec(align(64)) VUINT32 RcpBitMask[16][1]; > > > > - __declspec(align(64)) VUINT32 poly_coeff3[16][1]; > > > > - __declspec(align(64)) VUINT32 poly_coeff2[16][1]; > > > > - __declspec(align(64)) VUINT32 poly_coeff1[16][1]; > > > > - __declspec(align(64)) VUINT32 poly_coeff0[16][1]; > > > > - __declspec(align(64)) VUINT32 Half[16][1]; > > > > - __declspec(align(64)) VUINT32 L2H[16][1]; > > > > - __declspec(align(64)) VUINT32 L2L[16][1]; > > > > - } __svml_satanh_data_internal_avx512; > > > > + typedef unsigned int VUINT32; > > > > + typedef struct{ > > > > + __declspec (align(64))VUINT32 Log_tbl_H[32][1]; > > > > + __declspec (align(64))VUINT32 Log_tbl_L[32][1]; > > > > + __declspec (align(64))VUINT32 One[16][1]; > > > > + __declspec (align(64))VUINT32 AbsMask[16][1]; > > > > + __declspec (align(64))VUINT32 AddB5[16][1]; > > > > + __declspec (align(64))VUINT32 RcpBitMask[16][1]; > > > > + __declspec (align(64))VUINT32 poly_coeff3[16][1]; > > > > + __declspec (align(64))VUINT32 poly_coeff2[16][1]; > > > > + __declspec (align(64))VUINT32 poly_coeff1[16][1]; > > > > + __declspec (align(64))VUINT32 poly_coeff0[16][1]; > > > > + __declspec (align(64))VUINT32 Half[16][1]; > > > > + __declspec (align(64))VUINT32 L2H[16][1]; > > > > + __declspec (align(64))VUINT32 L2L[16][1]; > > > > + }__svml_satanh_data_internal_avx512; > > > > #endif > > > > __svml_satanh_data_internal_avx512: > > > > - /*== Log_tbl_H ==*/ > > > > - .long 0x00000000 > > > > - .long 0x3cfc0000 > > > > - .long 0x3d780000 > > > > - .long 0x3db78000 > > > > - .long 0x3df10000 > > > > - .long 0x3e14c000 > > > > - .long 0x3e300000 > > > > - .long 0x3e4a8000 > > > > - .long 0x3e648000 > > > > - .long 0x3e7dc000 > > > > - .long 0x3e8b4000 > > > > - .long 0x3e974000 > > > > - .long 0x3ea30000 > > > > - .long 0x3eae8000 > > > > - .long 0x3eb9c000 > > > > - .long 0x3ec4e000 > > > > - .long 0x3ecfa000 > > > > - .long 0x3eda2000 > > > > - .long 0x3ee48000 > > > > - .long 0x3eeea000 > > > > - .long 0x3ef8a000 > > > > - .long 0x3f013000 > > > > - .long 0x3f05f000 > > > > - .long 0x3f0aa000 > > > > - .long 0x3f0f4000 > > > > - .long 0x3f13d000 > > > > - .long 0x3f184000 > > > > - .long 0x3f1ca000 > > > > - .long 0x3f20f000 > > > > - .long 0x3f252000 > > > > - .long 0x3f295000 > > > > - .long 0x3f2d7000 > > > > - /*== Log_tbl_L ==*/ > > > > - .align 64 > > > > - .long 0x00000000 > > > > - .long 0x3726c39e > > > > - .long 0x38a30c01 > > > > - .long 0x37528ae5 > > > > - .long 0x38e0edc5 > > > > - .long 0xb8ab41f8 > > > > - .long 0xb7cf8f58 > > > > - .long 0x3896a73d > > > > - .long 0xb5838656 > > > > - .long 0x380c36af > > > > - .long 0xb8235454 > > > > - .long 0x3862bae1 > > > > - .long 0x38c5e10e > > > > - .long 0x38dedfac > > > > - .long 0x38ebfb5e > > > > - .long 0xb8e63c9f > > > > - .long 0xb85c1340 > > > > - .long 0x38777bcd > > > > - .long 0xb6038656 > > > > - .long 0x37d40984 > > > > - .long 0xb8b85028 > > > > - .long 0xb8ad5a5a > > > > - .long 0x3865c84a > > > > - .long 0x38c3d2f5 > > > > - .long 0x383ebce1 > > > > - .long 0xb8a1ed76 > > > > - .long 0xb7a332c4 > > > > - .long 0xb779654f > > > > - .long 0xb8602f73 > > > > - .long 0x38f85db0 > > > > - .long 0x37b4996f > > > > - .long 0xb8bfb3ca > > > > - /*== One ==*/ > > > > - .align 64 > > > > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > > - /*== AbsMask ==*/ > > > > - .align 64 > > > > - .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > > > > - /*== AddB5 ==*/ > > > > - .align 64 > > > > - .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > > > > - /*== RcpBitMask ==*/ > > > > - .align 64 > > > > - .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > > > > - /*== poly_coeff3 ==*/ > > > > - .align 64 > > > > - .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > > > > - /*== poly_coeff2 ==*/ > > > > - .align 64 > > > > - .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > > > > - /*== poly_coeff1 ==*/ > > > > - .align 64 > > > > - .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > > > > - /*== poly_coeff0 ==*/ > > > > - .align 64 > > > > - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > > - /*== Half ==*/ > > > > - .align 64 > > > > - .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > > > > - /*== L2H = log(2)_high ==*/ > > > > - .align 64 > > > > - .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > > > > - /*== L2L = log(2)_low ==*/ > > > > - .align 64 > > > > - .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > > > > - .align 64 > > > > - .type __svml_satanh_data_internal_avx512,@object > > > > - .size __svml_satanh_data_internal_avx512,.-__svml_satanh_data_internal_avx512 > > > > + /* == Log_tbl_H ==. */ > > > > + .long 0x00000000 > > > > + .long 0x3cfc0000 > > > > + .long 0x3d780000 > > > > + .long 0x3db78000 > > > > + .long 0x3df10000 > > > > + .long 0x3e14c000 > > > > + .long 0x3e300000 > > > > + .long 0x3e4a8000 > > > > + .long 0x3e648000 > > > > + .long 0x3e7dc000 > > > > + .long 0x3e8b4000 > > > > + .long 0x3e974000 > > > > + .long 0x3ea30000 > > > > + .long 0x3eae8000 > > > > + .long 0x3eb9c000 > > > > + .long 0x3ec4e000 > > > > + .long 0x3ecfa000 > > > > + .long 0x3eda2000 > > > > + .long 0x3ee48000 > > > > + .long 0x3eeea000 > > > > + .long 0x3ef8a000 > > > > + .long 0x3f013000 > > > > + .long 0x3f05f000 > > > > + .long 0x3f0aa000 > > > > + .long 0x3f0f4000 > > > > + .long 0x3f13d000 > > > > + .long 0x3f184000 > > > > + .long 0x3f1ca000 > > > > + .long 0x3f20f000 > > > > + .long 0x3f252000 > > > > + .long 0x3f295000 > > > > + .long 0x3f2d7000 > > > > + /* == Log_tbl_L ==. */ > > > > + .align 64 > > > > + .long 0x00000000 > > > > + .long 0x3726c39e > > > > + .long 0x38a30c01 > > > > + .long 0x37528ae5 > > > > + .long 0x38e0edc5 > > > > + .long 0xb8ab41f8 > > > > + .long 0xb7cf8f58 > > > > + .long 0x3896a73d > > > > + .long 0xb5838656 > > > > + .long 0x380c36af > > > > + .long 0xb8235454 > > > > + .long 0x3862bae1 > > > > + .long 0x38c5e10e > > > > + .long 0x38dedfac > > > > + .long 0x38ebfb5e > > > > + .long 0xb8e63c9f > > > > + .long 0xb85c1340 > > > > + .long 0x38777bcd > > > > + .long 0xb6038656 > > > > + .long 0x37d40984 > > > > + .long 0xb8b85028 > > > > + .long 0xb8ad5a5a > > > > + .long 0x3865c84a > > > > + .long 0x38c3d2f5 > > > > + .long 0x383ebce1 > > > > + .long 0xb8a1ed76 > > > > + .long 0xb7a332c4 > > > > + .long 0xb779654f > > > > + .long 0xb8602f73 > > > > + .long 0x38f85db0 > > > > + .long 0x37b4996f > > > > + .long 0xb8bfb3ca > > > > + /* == One ==. */ > > > > + .align 64 > > > > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > > + /* == AbsMask ==. */ > > > > + .align 64 > > > > + .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff > > > > + /* == AddB5 ==. */ > > > > + .align 64 > > > > + .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 > > > > + /* == RcpBitMask ==. */ > > > > + .align 64 > > > > + .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 > > > > + /* == poly_coeff3 ==. */ > > > > + .align 64 > > > > + .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 > > > > + /* == poly_coeff2 ==. */ > > > > + .align 64 > > > > + .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e > > > > + /* == poly_coeff1 ==. */ > > > > + .align 64 > > > > + .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 > > > > + /* == poly_coeff0 ==. */ > > > > + .align 64 > > > > + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 > > > > + /* == Half ==. */ > > > > + .align 64 > > > > + .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 > > > > + /* == L2H = log(2)_high ==. */ > > > > + .align 64 > > > > + .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 > > > > + /* == L2L = log(2)_low ==. */ > > > > + .align 64 > > > > + .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 > > > > + .align 64 > > > > + .type __svml_satanh_data_internal_avx512, @object > > > > + .size __svml_satanh_data_internal_avx512, .-__svml_satanh_data_internal_avx512 > > > > -- > > > > 2.25.1 > > > >
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S index f863f4f959..ed90a427a6 100644 --- a/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S +++ b/sysdeps/x86_64/fpu/multiarch/svml_s_atanhf16_core_avx512.S @@ -33,361 +33,348 @@ /* Offsets for data table __svml_satanh_data_internal_avx512 */ -#define Log_tbl_H 0 -#define Log_tbl_L 128 -#define One 256 -#define AbsMask 320 -#define AddB5 384 -#define RcpBitMask 448 -#define poly_coeff3 512 -#define poly_coeff2 576 -#define poly_coeff1 640 -#define poly_coeff0 704 -#define Half 768 -#define L2H 832 -#define L2L 896 +#define Log_tbl_H 0 +#define Log_tbl_L 128 +#define One 256 +#define AbsMask 320 +#define AddB5 384 +#define RcpBitMask 448 +#define poly_coeff3 512 +#define poly_coeff2 576 +#define poly_coeff1 640 +#define poly_coeff0 704 +#define Half 768 +#define L2H 832 +#define L2L 896 #include <sysdep.h> - .text - .section .text.exex512,"ax",@progbits + .text + .section .text.exex512, "ax", @progbits ENTRY(_ZGVeN16v_atanhf_skx) - pushq %rbp - cfi_def_cfa_offset(16) - movq %rsp, %rbp - cfi_def_cfa(6, 16) - cfi_offset(6, -16) - andq $-64, %rsp - subq $192, %rsp - vmovups One+__svml_satanh_data_internal_avx512(%rip), %zmm4 - -/* round reciprocals to 1+5b mantissas */ - vmovups AddB5+__svml_satanh_data_internal_avx512(%rip), %zmm14 - vmovups RcpBitMask+__svml_satanh_data_internal_avx512(%rip), %zmm1 - vmovaps %zmm0, %zmm11 - vandps AbsMask+__svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 - -/* 1+y */ - vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 - -/* 1-y */ - vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 - vxorps %zmm6, %zmm11, %zmm10 - -/* Yp_high */ - vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 - -/* -Ym_high */ - vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 - -/* RcpP ~ 1/Yp */ - vrcp14ps %zmm9, %zmm12 - -/* RcpM ~ 1/Ym */ - vrcp14ps %zmm8, %zmm13 - -/* input outside (-1, 1) ? */ - vcmpps $21, {sae}, %zmm4, %zmm6, %k0 - vpaddd %zmm14, %zmm12, %zmm15 - vpaddd %zmm14, %zmm13, %zmm0 - -/* Yp_low */ - vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 - vandps %zmm1, %zmm15, %zmm7 - vandps %zmm1, %zmm0, %zmm12 - -/* Ym_low */ - vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 - -/* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low */ - vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 - -/* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low */ - vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 - vmovups Log_tbl_L+__svml_satanh_data_internal_avx512(%rip), %zmm8 - vmovups Log_tbl_L+64+__svml_satanh_data_internal_avx512(%rip), %zmm13 - -/* exponents */ - vgetexpps {sae}, %zmm7, %zmm15 - vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 - -/* Table lookups */ - vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 - vgetexpps {sae}, %zmm12, %zmm14 - vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 - -/* Prepare table index */ - vpsrld $18, %zmm7, %zmm3 - vpsrld $18, %zmm12, %zmm2 - vmovups Log_tbl_H+64+__svml_satanh_data_internal_avx512(%rip), %zmm7 - vmovups poly_coeff1+__svml_satanh_data_internal_avx512(%rip), %zmm12 - -/* Km-Kp */ - vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 - kmovw %k0, %edx - vmovaps %zmm3, %zmm0 - vpermi2ps %zmm13, %zmm8, %zmm3 - vpermt2ps %zmm13, %zmm2, %zmm8 - vpermi2ps %zmm7, %zmm6, %zmm0 - vpermt2ps %zmm7, %zmm2, %zmm6 - vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 - -/* K*L2H + Th */ - vmovups L2H+__svml_satanh_data_internal_avx512(%rip), %zmm2 - -/* K*L2L + Tl */ - vmovups L2L+__svml_satanh_data_internal_avx512(%rip), %zmm3 - -/* polynomials */ - vmovups poly_coeff3+__svml_satanh_data_internal_avx512(%rip), %zmm7 - vmovups poly_coeff0+__svml_satanh_data_internal_avx512(%rip), %zmm13 - -/* table values */ - vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 - vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 - vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 - vmovups poly_coeff2+__svml_satanh_data_internal_avx512(%rip), %zmm3 - vmovaps %zmm3, %zmm2 - vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 - vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 - vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 - vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 - vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 - vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 - -/* (K*L2L + Tl) + Rp*PolyP */ - vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 - vorps Half+__svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 - -/* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM */ - vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 - vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 - vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 - testl %edx, %edx - -/* Go to special inputs processing branch */ - jne L(SPECIAL_VALUES_BRANCH) - # LOE rbx r12 r13 r14 r15 edx zmm0 zmm11 - -/* Restore registers - * and exit the function - */ + pushq %rbp + cfi_def_cfa_offset (16) + movq %rsp, %rbp + cfi_def_cfa (6, 16) + cfi_offset (6, -16) + andq $-64, %rsp + subq $192, %rsp + vmovups One + __svml_satanh_data_internal_avx512(%rip), %zmm4 + + /* round reciprocals to 1+5b mantissas. */ + vmovups AddB5 + __svml_satanh_data_internal_avx512(%rip), %zmm14 + vmovups RcpBitMask + __svml_satanh_data_internal_avx512(%rip), %zmm1 + vmovaps %zmm0, %zmm11 + vandps AbsMask + __svml_satanh_data_internal_avx512(%rip), %zmm11, %zmm6 + + /* 1+y. */ + vaddps {rn-sae}, %zmm4, %zmm6, %zmm9 + + /* 1-y. */ + vsubps {rn-sae}, %zmm6, %zmm4, %zmm8 + vxorps %zmm6, %zmm11, %zmm10 + + /* Yp_high. */ + vsubps {rn-sae}, %zmm4, %zmm9, %zmm2 + + /* -Ym_high. */ + vsubps {rn-sae}, %zmm4, %zmm8, %zmm5 + + /* RcpP ~ 1/Yp. */ + vrcp14ps %zmm9, %zmm12 + + /* RcpM ~ 1/Ym. */ + vrcp14ps %zmm8, %zmm13 + + /* input outside (-1, 1) ?. */ + vcmpps $21, {sae}, %zmm4, %zmm6, %k0 + vpaddd %zmm14, %zmm12, %zmm15 + vpaddd %zmm14, %zmm13, %zmm0 + + /* Yp_low. */ + vsubps {rn-sae}, %zmm2, %zmm6, %zmm3 + vandps %zmm1, %zmm15, %zmm7 + vandps %zmm1, %zmm0, %zmm12 + + /* Ym_low. */ + vaddps {rn-sae}, %zmm5, %zmm6, %zmm5 + + /* Reduced argument: Rp = (RcpP*Yp - 1)+RcpP*Yp_low. */ + vfmsub213ps {rn-sae}, %zmm4, %zmm7, %zmm9 + + /* Reduced argument: Rm = (RcpM*Ym - 1)+RcpM*Ym_low. */ + vfmsub231ps {rn-sae}, %zmm12, %zmm8, %zmm4 + vmovups Log_tbl_L + __svml_satanh_data_internal_avx512(%rip), %zmm8 + vmovups Log_tbl_L + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm13 + + /* exponents. */ + vgetexpps {sae}, %zmm7, %zmm15 + vfmadd231ps {rn-sae}, %zmm7, %zmm3, %zmm9 + + /* Table lookups. */ + vmovups __svml_satanh_data_internal_avx512(%rip), %zmm6 + vgetexpps {sae}, %zmm12, %zmm14 + vfnmadd231ps {rn-sae}, %zmm12, %zmm5, %zmm4 + + /* Prepare table index. */ + vpsrld $18, %zmm7, %zmm3 + vpsrld $18, %zmm12, %zmm2 + vmovups Log_tbl_H + 64 + __svml_satanh_data_internal_avx512(%rip), %zmm7 + vmovups poly_coeff1 + __svml_satanh_data_internal_avx512(%rip), %zmm12 + + /* Km-Kp. */ + vsubps {rn-sae}, %zmm15, %zmm14, %zmm1 + kmovw %k0, %edx + vmovaps %zmm3, %zmm0 + vpermi2ps %zmm13, %zmm8, %zmm3 + vpermt2ps %zmm13, %zmm2, %zmm8 + vpermi2ps %zmm7, %zmm6, %zmm0 + vpermt2ps %zmm7, %zmm2, %zmm6 + vsubps {rn-sae}, %zmm3, %zmm8, %zmm5 + + /* K*L2H + Th. */ + vmovups L2H + __svml_satanh_data_internal_avx512(%rip), %zmm2 + + /* K*L2L + Tl. */ + vmovups L2L + __svml_satanh_data_internal_avx512(%rip), %zmm3 + + /* polynomials. */ + vmovups poly_coeff3 + __svml_satanh_data_internal_avx512(%rip), %zmm7 + vmovups poly_coeff0 + __svml_satanh_data_internal_avx512(%rip), %zmm13 + + /* table values. */ + vsubps {rn-sae}, %zmm0, %zmm6, %zmm0 + vfmadd231ps {rn-sae}, %zmm1, %zmm2, %zmm0 + vfmadd213ps {rn-sae}, %zmm5, %zmm3, %zmm1 + vmovups poly_coeff2 + __svml_satanh_data_internal_avx512(%rip), %zmm3 + vmovaps %zmm3, %zmm2 + vfmadd231ps {rn-sae}, %zmm9, %zmm7, %zmm2 + vfmadd231ps {rn-sae}, %zmm4, %zmm7, %zmm3 + vfmadd213ps {rn-sae}, %zmm12, %zmm9, %zmm2 + vfmadd213ps {rn-sae}, %zmm12, %zmm4, %zmm3 + vfmadd213ps {rn-sae}, %zmm13, %zmm9, %zmm2 + vfmadd213ps {rn-sae}, %zmm13, %zmm4, %zmm3 + + /* (K*L2L + Tl) + Rp*PolyP. */ + vfmadd213ps {rn-sae}, %zmm1, %zmm9, %zmm2 + vorps Half + __svml_satanh_data_internal_avx512(%rip), %zmm10, %zmm9 + + /* (K*L2L + Tl) + Rp*PolyP -Rm*PolyM. */ + vfnmadd213ps {rn-sae}, %zmm2, %zmm4, %zmm3 + vaddps {rn-sae}, %zmm3, %zmm0, %zmm4 + vmulps {rn-sae}, %zmm9, %zmm4, %zmm0 + testl %edx, %edx + + /* Go to special inputs processing branch. */ + jne L(SPECIAL_VALUES_BRANCH) + + /* Restore registers * and exit the function. */ L(EXIT): - movq %rbp, %rsp - popq %rbp - cfi_def_cfa(7, 8) - cfi_restore(6) - ret - cfi_def_cfa(6, 16) - cfi_offset(6, -16) - -/* Branch to process - * special inputs - */ + movq %rbp, %rsp + popq %rbp + cfi_def_cfa (7, 8) + cfi_restore (6) + ret + cfi_def_cfa (6, 16) + cfi_offset (6, -16) + + /* Branch to process special inputs. */ L(SPECIAL_VALUES_BRANCH): - vmovups %zmm11, 64(%rsp) - vmovups %zmm0, 128(%rsp) - # LOE rbx r12 r13 r14 r15 edx zmm0 - - xorl %eax, %eax - # LOE rbx r12 r13 r14 r15 eax edx - - vzeroupper - movq %r12, 16(%rsp) - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 - movl %eax, %r12d - movq %r13, 8(%rsp) - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 - movl %edx, %r13d - movq %r14, (%rsp) - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 - # LOE rbx r15 r12d r13d - -/* Range mask - * bits check - */ + vmovups %zmm11, 64(%rsp) + vmovups %zmm0, 128(%rsp) + + xorl %eax, %eax + + vzeroupper + movq %r12, 16(%rsp) + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 + movl %eax, %r12d + movq %r13, 8(%rsp) + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 + movl %edx, %r13d + movq %r14, (%rsp) + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 + + /* Range mask * bits check. */ L(RANGEMASK_CHECK): - btl %r12d, %r13d + btl %r12d, %r13d -/* Call scalar math function */ - jc L(SCALAR_MATH_CALL) - # LOE rbx r15 r12d r13d + /* Call scalar math function. */ + jc L(SCALAR_MATH_CALL) -/* Special inputs - * processing loop - */ + /* Special inputs processing loop. */ L(SPECIAL_VALUES_LOOP): - incl %r12d - cmpl $16, %r12d - -/* Check bits in range mask */ - jl L(RANGEMASK_CHECK) - # LOE rbx r15 r12d r13d - - movq 16(%rsp), %r12 - cfi_restore(12) - movq 8(%rsp), %r13 - cfi_restore(13) - movq (%rsp), %r14 - cfi_restore(14) - vmovups 128(%rsp), %zmm0 - -/* Go to exit */ - jmp L(EXIT) - /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus) */ - .cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x50, 0xff, 0xff, 0xff, 0x22 - /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus) */ - .cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x48, 0xff, 0xff, 0xff, 0x22 - /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus) */ - .cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xc0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0x40, 0xff, 0xff, 0xff, 0x22 - # LOE rbx r12 r13 r14 r15 zmm0 - -/* Scalar math fucntion call - * to process special input - */ + incl %r12d + cmpl $16, %r12d + + /* Check bits in range mask. */ + jl L(RANGEMASK_CHECK) + + movq 16(%rsp), %r12 + cfi_restore (12) + movq 8(%rsp), %r13 + cfi_restore (13) + movq (%rsp), %r14 + cfi_restore (14) + vmovups 128(%rsp), %zmm0 + + /* Go to exit. */ + jmp L(EXIT) + /* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: + -64; DW_OP_and; DW_OP_const4s: -176; DW_OP_plus). */ + .cfi_escape 0x10 , 0x0c , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x50 , 0xff , 0xff , 0xff , 0x22 + /* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: + -64; DW_OP_and; DW_OP_const4s: -184; DW_OP_plus). */ + .cfi_escape 0x10 , 0x0d , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x48 , 0xff , 0xff , 0xff , 0x22 + /* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: + -64; DW_OP_and; DW_OP_const4s: -192; DW_OP_plus). */ + .cfi_escape 0x10 , 0x0e , 0x0e , 0x38 , 0x1c , 0x0d , 0xc0 , 0xff , 0xff , 0xff , 0x1a , 0x0d , 0x40 , 0xff , 0xff , 0xff , 0x22 + + /* Scalar math fucntion call to process special input. */ L(SCALAR_MATH_CALL): - movl %r12d, %r14d - movss 64(%rsp,%r14,4), %xmm0 - call atanhf@PLT - # LOE rbx r14 r15 r12d r13d xmm0 + movl %r12d, %r14d + movss 64(%rsp, %r14, 4), %xmm0 + call atanhf@PLT - movss %xmm0, 128(%rsp,%r14,4) + movss %xmm0, 128(%rsp, %r14, 4) -/* Process special inputs in loop */ - jmp L(SPECIAL_VALUES_LOOP) - # LOE rbx r15 r12d r13d + /* Process special inputs in loop. */ + jmp L(SPECIAL_VALUES_LOOP) END(_ZGVeN16v_atanhf_skx) - .section .rodata, "a" - .align 64 + .section .rodata, "a" + .align 64 #ifdef __svml_satanh_data_internal_avx512_typedef -typedef unsigned int VUINT32; -typedef struct { - __declspec(align(64)) VUINT32 Log_tbl_H[32][1]; - __declspec(align(64)) VUINT32 Log_tbl_L[32][1]; - __declspec(align(64)) VUINT32 One[16][1]; - __declspec(align(64)) VUINT32 AbsMask[16][1]; - __declspec(align(64)) VUINT32 AddB5[16][1]; - __declspec(align(64)) VUINT32 RcpBitMask[16][1]; - __declspec(align(64)) VUINT32 poly_coeff3[16][1]; - __declspec(align(64)) VUINT32 poly_coeff2[16][1]; - __declspec(align(64)) VUINT32 poly_coeff1[16][1]; - __declspec(align(64)) VUINT32 poly_coeff0[16][1]; - __declspec(align(64)) VUINT32 Half[16][1]; - __declspec(align(64)) VUINT32 L2H[16][1]; - __declspec(align(64)) VUINT32 L2L[16][1]; - } __svml_satanh_data_internal_avx512; + typedef unsigned int VUINT32; + typedef struct{ + __declspec (align(64))VUINT32 Log_tbl_H[32][1]; + __declspec (align(64))VUINT32 Log_tbl_L[32][1]; + __declspec (align(64))VUINT32 One[16][1]; + __declspec (align(64))VUINT32 AbsMask[16][1]; + __declspec (align(64))VUINT32 AddB5[16][1]; + __declspec (align(64))VUINT32 RcpBitMask[16][1]; + __declspec (align(64))VUINT32 poly_coeff3[16][1]; + __declspec (align(64))VUINT32 poly_coeff2[16][1]; + __declspec (align(64))VUINT32 poly_coeff1[16][1]; + __declspec (align(64))VUINT32 poly_coeff0[16][1]; + __declspec (align(64))VUINT32 Half[16][1]; + __declspec (align(64))VUINT32 L2H[16][1]; + __declspec (align(64))VUINT32 L2L[16][1]; + }__svml_satanh_data_internal_avx512; #endif __svml_satanh_data_internal_avx512: - /*== Log_tbl_H ==*/ - .long 0x00000000 - .long 0x3cfc0000 - .long 0x3d780000 - .long 0x3db78000 - .long 0x3df10000 - .long 0x3e14c000 - .long 0x3e300000 - .long 0x3e4a8000 - .long 0x3e648000 - .long 0x3e7dc000 - .long 0x3e8b4000 - .long 0x3e974000 - .long 0x3ea30000 - .long 0x3eae8000 - .long 0x3eb9c000 - .long 0x3ec4e000 - .long 0x3ecfa000 - .long 0x3eda2000 - .long 0x3ee48000 - .long 0x3eeea000 - .long 0x3ef8a000 - .long 0x3f013000 - .long 0x3f05f000 - .long 0x3f0aa000 - .long 0x3f0f4000 - .long 0x3f13d000 - .long 0x3f184000 - .long 0x3f1ca000 - .long 0x3f20f000 - .long 0x3f252000 - .long 0x3f295000 - .long 0x3f2d7000 - /*== Log_tbl_L ==*/ - .align 64 - .long 0x00000000 - .long 0x3726c39e - .long 0x38a30c01 - .long 0x37528ae5 - .long 0x38e0edc5 - .long 0xb8ab41f8 - .long 0xb7cf8f58 - .long 0x3896a73d - .long 0xb5838656 - .long 0x380c36af - .long 0xb8235454 - .long 0x3862bae1 - .long 0x38c5e10e - .long 0x38dedfac - .long 0x38ebfb5e - .long 0xb8e63c9f - .long 0xb85c1340 - .long 0x38777bcd - .long 0xb6038656 - .long 0x37d40984 - .long 0xb8b85028 - .long 0xb8ad5a5a - .long 0x3865c84a - .long 0x38c3d2f5 - .long 0x383ebce1 - .long 0xb8a1ed76 - .long 0xb7a332c4 - .long 0xb779654f - .long 0xb8602f73 - .long 0x38f85db0 - .long 0x37b4996f - .long 0xb8bfb3ca - /*== One ==*/ - .align 64 - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 - /*== AbsMask ==*/ - .align 64 - .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff - /*== AddB5 ==*/ - .align 64 - .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 - /*== RcpBitMask ==*/ - .align 64 - .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 - /*== poly_coeff3 ==*/ - .align 64 - .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 - /*== poly_coeff2 ==*/ - .align 64 - .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e - /*== poly_coeff1 ==*/ - .align 64 - .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 - /*== poly_coeff0 ==*/ - .align 64 - .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 - /*== Half ==*/ - .align 64 - .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 - /*== L2H = log(2)_high ==*/ - .align 64 - .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 - /*== L2L = log(2)_low ==*/ - .align 64 - .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 - .align 64 - .type __svml_satanh_data_internal_avx512,@object - .size __svml_satanh_data_internal_avx512,.-__svml_satanh_data_internal_avx512 + /* == Log_tbl_H ==. */ + .long 0x00000000 + .long 0x3cfc0000 + .long 0x3d780000 + .long 0x3db78000 + .long 0x3df10000 + .long 0x3e14c000 + .long 0x3e300000 + .long 0x3e4a8000 + .long 0x3e648000 + .long 0x3e7dc000 + .long 0x3e8b4000 + .long 0x3e974000 + .long 0x3ea30000 + .long 0x3eae8000 + .long 0x3eb9c000 + .long 0x3ec4e000 + .long 0x3ecfa000 + .long 0x3eda2000 + .long 0x3ee48000 + .long 0x3eeea000 + .long 0x3ef8a000 + .long 0x3f013000 + .long 0x3f05f000 + .long 0x3f0aa000 + .long 0x3f0f4000 + .long 0x3f13d000 + .long 0x3f184000 + .long 0x3f1ca000 + .long 0x3f20f000 + .long 0x3f252000 + .long 0x3f295000 + .long 0x3f2d7000 + /* == Log_tbl_L ==. */ + .align 64 + .long 0x00000000 + .long 0x3726c39e + .long 0x38a30c01 + .long 0x37528ae5 + .long 0x38e0edc5 + .long 0xb8ab41f8 + .long 0xb7cf8f58 + .long 0x3896a73d + .long 0xb5838656 + .long 0x380c36af + .long 0xb8235454 + .long 0x3862bae1 + .long 0x38c5e10e + .long 0x38dedfac + .long 0x38ebfb5e + .long 0xb8e63c9f + .long 0xb85c1340 + .long 0x38777bcd + .long 0xb6038656 + .long 0x37d40984 + .long 0xb8b85028 + .long 0xb8ad5a5a + .long 0x3865c84a + .long 0x38c3d2f5 + .long 0x383ebce1 + .long 0xb8a1ed76 + .long 0xb7a332c4 + .long 0xb779654f + .long 0xb8602f73 + .long 0x38f85db0 + .long 0x37b4996f + .long 0xb8bfb3ca + /* == One ==. */ + .align 64 + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 + /* == AbsMask ==. */ + .align 64 + .long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff + /* == AddB5 ==. */ + .align 64 + .long 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000, 0x00020000 + /* == RcpBitMask ==. */ + .align 64 + .long 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000, 0xfffc0000 + /* == poly_coeff3 ==. */ + .align 64 + .long 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810, 0xbe800810 + /* == poly_coeff2 ==. */ + .align 64 + .long 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e, 0x3eaab11e + /* == poly_coeff1 ==. */ + .align 64 + .long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 + /* == poly_coeff0 ==. */ + .align 64 + .long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 + /* == Half ==. */ + .align 64 + .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 + /* == L2H = log(2)_high ==. */ + .align 64 + .long 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000, 0x3f317000 + /* == L2L = log(2)_low ==. */ + .align 64 + .long 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4, 0x3805fdf4 + .align 64 + .type __svml_satanh_data_internal_avx512, @object + .size __svml_satanh_data_internal_avx512, .-__svml_satanh_data_internal_avx512
Reformats to match style of other hand coded assembly files. The changes are: 1. Replace 8x space with tab before instructions. 2. After instruction len < 8 use tab. 3. After instruction len >= 8 use space. 4. 1 Space after comma between instruction operands. 5. Indent comments similiar with code. 6. Make comments complete sentences. 7. Tab after '#define' 8. Spaces at '#' representing the depth. The final executable is unchanged by this commit. --- The changes for this patch where made with the following script: https://github.com/goldsteinn/assembly-beautifier The goal of this patch is just to reformat the code so it is more human friendly and try create a style that future patches will be based on. If this patch is accepted ensuing patches to optimize the performance of svml_s_atanhf16_core_avx512.S will be based on this patch. .../multiarch/svml_s_atanhf16_core_avx512.S | 655 +++++++++--------- 1 file changed, 321 insertions(+), 334 deletions(-)