diff mbox series

[109/126] x86_64: Fix svml_s_sinhf16_core_avx512.S code formatting

Message ID 20220307150201.10590-110-skpgkp2@gmail.com
State New
Headers show
Series x86_64: Fix libmvec assembly code formatting | expand

Commit Message

Sunil Pandey March 7, 2022, 3:01 p.m. UTC
This commit contains following formatting changes

1. Instructions proceeded by a tab.
2. Instruction less than 8 characters in length have a tab
   between it and the first operand.
3. Instruction greater than 7 characters in length have a
   space between it and the first operand.
4. Tabs after `#define`d names and their value.
5. 8 space at the beginning of line replaced by tab.
6. Indent comments with code.
7. Remove redundent .text section.
---
 .../multiarch/svml_s_sinhf16_core_avx512.S    | 510 +++++++++---------
 1 file changed, 254 insertions(+), 256 deletions(-)
diff mbox series

Patch

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf16_core_avx512.S
index 9e4f2f16a3..fad4847f28 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf16_core_avx512.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinhf16_core_avx512.S
@@ -34,285 +34,283 @@ 
 
 /* Offsets for data table __svml_ssinh_data_internal
  */
-#define _sInvLn2                      	0
-#define _sLn2hi                       	64
-#define _sLn2lo                       	128
-#define _sSign                        	192
-#define _sShifter                     	256
-#define _iDomainRange                 	320
-#define _sPC1                         	384
-#define _sPC2                         	448
-#define _sPC3                         	512
-#define _sPC4                         	576
-#define _sPC5                         	640
-#define _sPC6                         	704
-#define _iHalf                        	768
+#define _sInvLn2			0
+#define _sLn2hi				64
+#define _sLn2lo				128
+#define _sSign				192
+#define _sShifter			256
+#define _iDomainRange			320
+#define _sPC1				384
+#define _sPC2				448
+#define _sPC3				512
+#define _sPC4				576
+#define _sPC5				640
+#define _sPC6				704
+#define _iHalf				768
 
 #include <sysdep.h>
 
-        .text
-	.section .text.exex512,"ax",@progbits
+	.section .text.exex512, "ax", @progbits
 ENTRY(_ZGVeN16v_sinhf_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
-        vmovaps   %zmm0, %zmm5
-
-/*
- *  Implementation
- *  Abs argument
- */
-        vandps    _sSign+__svml_ssinh_data_internal(%rip), %zmm5, %zmm4
-
-/*
- * Check for overflow\underflow
- * MORE faster than GE?
- */
-        vpternlogd $255, %zmm6, %zmm6, %zmm6
-        vmovups   _sShifter+__svml_ssinh_data_internal(%rip), %zmm7
-
-/*
- *  Load argument
- * dM = x/log(2) + RShifter
- */
-        vmovups   _sInvLn2+__svml_ssinh_data_internal(%rip), %zmm11
-        vmovups   _sLn2hi+__svml_ssinh_data_internal(%rip), %zmm8
-        vmovups   _sLn2lo+__svml_ssinh_data_internal(%rip), %zmm10
-        vmovups   _iHalf+__svml_ssinh_data_internal(%rip), %zmm12
-        vmovups   _sPC5+__svml_ssinh_data_internal(%rip), %zmm0
-        vmovups   _sPC6+__svml_ssinh_data_internal(%rip), %zmm3
-
-/* x^2 */
-        vmovups   _sPC2+__svml_ssinh_data_internal(%rip), %zmm2
-        vxorps    %zmm5, %zmm4, %zmm1
-        vfmadd213ps {rn-sae}, %zmm7, %zmm1, %zmm11
-        vpcmpd    $2, _iDomainRange+__svml_ssinh_data_internal(%rip), %zmm1, %k1
-
-/*
- *  G1,G2 2^N,2^(-N)
- * iM now is an EXP(2^N)
- */
-        vpslld    $23, %zmm11, %zmm13
-
-/*
- *  R
- * sN = sM - RShifter
- */
-        vsubps    {rn-sae}, %zmm7, %zmm11, %zmm9
-        vpaddd    %zmm13, %zmm12, %zmm14
-        vpsubd    %zmm13, %zmm12, %zmm15
-
-/* sG1 = 2^(N-1)+2^(-N-1) */
-        vaddps    {rn-sae}, %zmm15, %zmm14, %zmm7
-        vpandnd   %zmm1, %zmm1, %zmm6{%k1}
-
-/* sR = sX - sN*Log2_hi */
-        vfnmadd231ps {rn-sae}, %zmm8, %zmm9, %zmm1
-        vptestmd  %zmm6, %zmm6, %k0
-
-/* sG2 = 2^(N-1)-2^(-N-1) */
-        vsubps    {rn-sae}, %zmm15, %zmm14, %zmm8
-
-/* sR = (sX - sN*Log2_hi) - sN*Log2_lo */
-        vfnmadd231ps {rn-sae}, %zmm10, %zmm9, %zmm1
-
-/*
- * sinh(r) = r*((a1=1)+r^2*(a3+r^2*(a5+{v1 r^2*a7})))) = r + r*(r^2*(a3+r^2*(a5+r^2*a7))) ....
- * sSinh_r = (a3+r^2*a5)
- */
-        vmovups   _sPC3+__svml_ssinh_data_internal(%rip), %zmm14
-        kmovw     %k0, %edx
-
-/* sR2 = sR^2 */
-        vmulps    {rn-sae}, %zmm1, %zmm1, %zmm6
-        vfmadd231ps {rn-sae}, %zmm6, %zmm0, %zmm14
-
-/* sSinh_r = r^2*(a3+r^2*a5) */
-        vmulps    {rn-sae}, %zmm6, %zmm14, %zmm0
-
-/* sSinh_r = r + r*(r^2*(a3+r^2*a5)) */
-        vfmadd213ps {rn-sae}, %zmm1, %zmm1, %zmm0
-
-/*
- * sinh(X) = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2)
- * sOut = (a4 +a6*sR2)
- */
-        vmovups   _sPC4+__svml_ssinh_data_internal(%rip), %zmm1
-        vfmadd231ps {rn-sae}, %zmm6, %zmm3, %zmm1
-
-/* sOut = a2+sR2*(a4+a6*sR2) */
-        vfmadd213ps {rn-sae}, %zmm2, %zmm6, %zmm1
-
-/* sOut = sR2*(a2+sR2*(a4+a6*sR2) */
-        vmulps    {rn-sae}, %zmm6, %zmm1, %zmm2
-
-/* sOut = sG2*sR2*(a2+sR2*(a4+a6*sR2) */
-        vmulps    {rn-sae}, %zmm8, %zmm2, %zmm3
-
-/* sOut = sG1*sinh(dR)+sG2*sR2*(a2+sR2*(a4+a6*sR2) */
-        vfmadd213ps {rn-sae}, %zmm3, %zmm0, %zmm7
-
-/* sOut = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2) */
-        vaddps    {rn-sae}, %zmm8, %zmm7, %zmm9
-
-/*  Ret H  */
-        vorps     %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 zmm5
-
-/* 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
+	vmovaps	%zmm0, %zmm5
+
+	/*
+	 *  Implementation
+	 *  Abs argument
+	 */
+	vandps	_sSign+__svml_ssinh_data_internal(%rip), %zmm5, %zmm4
+
+	/*
+	 * Check for overflow\underflow
+	 * MORE faster than GE?
+	 */
+	vpternlogd $255, %zmm6, %zmm6, %zmm6
+	vmovups	_sShifter+__svml_ssinh_data_internal(%rip), %zmm7
+
+	/*
+	 *  Load argument
+	 * dM = x/log(2) + RShifter
+	 */
+	vmovups	_sInvLn2+__svml_ssinh_data_internal(%rip), %zmm11
+	vmovups	_sLn2hi+__svml_ssinh_data_internal(%rip), %zmm8
+	vmovups	_sLn2lo+__svml_ssinh_data_internal(%rip), %zmm10
+	vmovups	_iHalf+__svml_ssinh_data_internal(%rip), %zmm12
+	vmovups	_sPC5+__svml_ssinh_data_internal(%rip), %zmm0
+	vmovups	_sPC6+__svml_ssinh_data_internal(%rip), %zmm3
+
+	/* x^2 */
+	vmovups	_sPC2+__svml_ssinh_data_internal(%rip), %zmm2
+	vxorps	%zmm5, %zmm4, %zmm1
+	vfmadd213ps {rn-sae}, %zmm7, %zmm1, %zmm11
+	vpcmpd	$2, _iDomainRange+__svml_ssinh_data_internal(%rip), %zmm1, %k1
+
+	/*
+	 *  G1, G2 2^N, 2^(-N)
+	 * iM now is an EXP(2^N)
+	 */
+	vpslld	$23, %zmm11, %zmm13
+
+	/*
+	 *  R
+	 * sN = sM - RShifter
+	 */
+	vsubps	{rn-sae}, %zmm7, %zmm11, %zmm9
+	vpaddd	%zmm13, %zmm12, %zmm14
+	vpsubd	%zmm13, %zmm12, %zmm15
+
+	/* sG1 = 2^(N-1)+2^(-N-1) */
+	vaddps	{rn-sae}, %zmm15, %zmm14, %zmm7
+	vpandnd	%zmm1, %zmm1, %zmm6{%k1}
+
+	/* sR = sX - sN*Log2_hi */
+	vfnmadd231ps {rn-sae}, %zmm8, %zmm9, %zmm1
+	vptestmd %zmm6, %zmm6, %k0
+
+	/* sG2 = 2^(N-1)-2^(-N-1) */
+	vsubps	{rn-sae}, %zmm15, %zmm14, %zmm8
+
+	/* sR = (sX - sN*Log2_hi) - sN*Log2_lo */
+	vfnmadd231ps {rn-sae}, %zmm10, %zmm9, %zmm1
+
+	/*
+	 * sinh(r) = r*((a1=1)+r^2*(a3+r^2*(a5+{v1 r^2*a7})))) = r + r*(r^2*(a3+r^2*(a5+r^2*a7))) ....
+	 * sSinh_r = (a3+r^2*a5)
+	 */
+	vmovups	_sPC3+__svml_ssinh_data_internal(%rip), %zmm14
+	kmovw	%k0, %edx
+
+	/* sR2 = sR^2 */
+	vmulps	{rn-sae}, %zmm1, %zmm1, %zmm6
+	vfmadd231ps {rn-sae}, %zmm6, %zmm0, %zmm14
+
+	/* sSinh_r = r^2*(a3+r^2*a5) */
+	vmulps	{rn-sae}, %zmm6, %zmm14, %zmm0
+
+	/* sSinh_r = r + r*(r^2*(a3+r^2*a5)) */
+	vfmadd213ps {rn-sae}, %zmm1, %zmm1, %zmm0
+
+	/*
+	 * sinh(X) = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2)
+	 * sOut = (a4 +a6*sR2)
+	 */
+	vmovups	_sPC4+__svml_ssinh_data_internal(%rip), %zmm1
+	vfmadd231ps {rn-sae}, %zmm6, %zmm3, %zmm1
+
+	/* sOut = a2+sR2*(a4+a6*sR2) */
+	vfmadd213ps {rn-sae}, %zmm2, %zmm6, %zmm1
+
+	/* sOut = sR2*(a2+sR2*(a4+a6*sR2) */
+	vmulps	{rn-sae}, %zmm6, %zmm1, %zmm2
+
+	/* sOut = sG2*sR2*(a2+sR2*(a4+a6*sR2) */
+	vmulps	{rn-sae}, %zmm8, %zmm2, %zmm3
+
+	/* sOut = sG1*sinh(dR)+sG2*sR2*(a2+sR2*(a4+a6*sR2) */
+	vfmadd213ps {rn-sae}, %zmm3, %zmm0, %zmm7
+
+	/* sOut = sG2 + sG1*sinh(dR) + sG2*sR2*(a2+sR2*(a4+a6*sR2) */
+	vaddps	{rn-sae}, %zmm8, %zmm7, %zmm9
+
+	/*  Ret H  */
+	vorps	%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 zmm5
+
+	/* 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   %zmm5, 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	%zmm5, 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
+	 */
 
 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)
+	# LOE rbx r15 r12d r13d
 
-/* 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)
+	# 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
+	 */
 
 L(SCALAR_MATH_CALL):
-        movl      %r12d, %r14d
-        movss     64(%rsp,%r14,4), %xmm0
-        call      sinhf@PLT
-                                # LOE rbx r14 r15 r12d r13d xmm0
+	movl	%r12d, %r14d
+	movss	64(%rsp, %r14, 4), %xmm0
+	call	sinhf@PLT
+	# LOE rbx r14 r15 r12d r13d xmm0
 
-        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)
+	# LOE rbx r15 r12d r13d
 END(_ZGVeN16v_sinhf_skx)
 
-        .section .rodata, "a"
-        .align 64
+	.section .rodata, "a"
+	.align	64
 
 #ifdef __svml_ssinh_data_internal_typedef
 typedef unsigned int VUINT32;
-typedef struct
-{
-        __declspec(align(64)) VUINT32 _sInvLn2[16][1];
-        __declspec(align(64)) VUINT32 _sLn2hi[16][1];
-        __declspec(align(64)) VUINT32 _sLn2lo[16][1];
-        __declspec(align(64)) VUINT32 _sSign[16][1];
-        __declspec(align(64)) VUINT32 _sShifter[16][1];
-        __declspec(align(64)) VUINT32 _iDomainRange[16][1];
-        __declspec(align(64)) VUINT32 _sPC1[16][1];
-        __declspec(align(64)) VUINT32 _sPC2[16][1];
-        __declspec(align(64)) VUINT32 _sPC3[16][1];
-        __declspec(align(64)) VUINT32 _sPC4[16][1];
-        __declspec(align(64)) VUINT32 _sPC5[16][1];
-        __declspec(align(64)) VUINT32 _sPC6[16][1];
-        __declspec(align(64)) VUINT32 _iHalf[16][1];
+typedef struct {
+	__declspec(align(64)) VUINT32 _sInvLn2[16][1];
+	__declspec(align(64)) VUINT32 _sLn2hi[16][1];
+	__declspec(align(64)) VUINT32 _sLn2lo[16][1];
+	__declspec(align(64)) VUINT32 _sSign[16][1];
+	__declspec(align(64)) VUINT32 _sShifter[16][1];
+	__declspec(align(64)) VUINT32 _iDomainRange[16][1];
+	__declspec(align(64)) VUINT32 _sPC1[16][1];
+	__declspec(align(64)) VUINT32 _sPC2[16][1];
+	__declspec(align(64)) VUINT32 _sPC3[16][1];
+	__declspec(align(64)) VUINT32 _sPC4[16][1];
+	__declspec(align(64)) VUINT32 _sPC5[16][1];
+	__declspec(align(64)) VUINT32 _sPC6[16][1];
+	__declspec(align(64)) VUINT32 _iHalf[16][1];
 } __svml_ssinh_data_internal;
 #endif
 __svml_ssinh_data_internal:
-        .long 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B           /* _sInvLn2  */  //k=0
-        .align 64
-        .long 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000           /* _sLn2hi   */
-        .align 64
-        .long 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4           /* _sLn2lo   */
-        .align 64
-        .long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000           /* _sSign    */
-        .align 64
-        .long 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000           /* _sShifter */
-        .align 64
-        .long 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E           /* _iDomainRange */
-        .align 64
-        .long 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000         /* _sPC1=1  */
-        .align 64
-        .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000         /* _sPC2  */
-        .align 64
-        .long 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57         /* _sPC3  */
-        .align 64
-        .long 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72         /* _sPC4  */
-        .align 64
-        .long 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461         /* _sPC5  */
-        .align 64
-        .long 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3         /* _sPC6  */
-        // Integer constants
-        .align 64
-        .long 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 /* _iHalf*/
-        .align 64
-        .type	__svml_ssinh_data_internal,@object
-        .size	__svml_ssinh_data_internal,.-__svml_ssinh_data_internal
+	.long	0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B, 0x3FB8AA3B /* _sInvLn2 */ // k=0
+	.align	64
+	.long	0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000, 0x3F317000 /* _sLn2hi */
+	.align	64
+	.long	0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4, 0x3805FDF4 /* _sLn2lo */
+	.align	64
+	.long	0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000 /* _sSign */
+	.align	64
+	.long	0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000, 0x4b400000 /* _sShifter */
+	.align	64
+	.long	0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E, 0x42AEAC4E /* _iDomainRange */
+	.align	64
+	.long	0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000, 0x3F800000 /* _sPC1=1 */
+	.align	64
+	.long	0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 /* _sPC2 */
+	.align	64
+	.long	0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57, 0x3e2aaa57 /* _sPC3 */
+	.align	64
+	.long	0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72, 0x3d2aaa72 /* _sPC4 */
+	.align	64
+	.long	0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461, 0x3c091461 /* _sPC5 */
+	.align	64
+	.long	0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3, 0x3ab6a8a3 /* _sPC6 */
+	// Integer constants
+	.align	64
+	.long	0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000, 0x3f000000 /* _iHalf */
+	.align	64
+	.type	__svml_ssinh_data_internal, @object
+	.size	__svml_ssinh_data_internal, .-__svml_ssinh_data_internal