---
gcc/config/aarch64/aarch64-protos.h | 3 +
gcc/config/aarch64/aarch64-simd.md | 2 +-
gcc/config/aarch64/aarch64.cc | 131 ++++++++++++++++++
gcc/config/aarch64/aarch64.md | 57 ++++++++
gcc/config/aarch64/iterators.md | 4 +
gcc/testsuite/gcc.target/aarch64/crc-1-pmul.c | 8 ++
.../gcc.target/aarch64/crc-10-pmul.c | 8 ++
.../gcc.target/aarch64/crc-12-pmul.c | 9 ++
.../gcc.target/aarch64/crc-13-pmul.c | 8 ++
.../gcc.target/aarch64/crc-14-pmul.c | 8 ++
.../gcc.target/aarch64/crc-17-pmul.c | 8 ++
.../gcc.target/aarch64/crc-18-pmul.c | 8 ++
.../gcc.target/aarch64/crc-21-pmul.c | 8 ++
.../gcc.target/aarch64/crc-22-pmul.c | 8 ++
.../gcc.target/aarch64/crc-23-pmul.c | 8 ++
gcc/testsuite/gcc.target/aarch64/crc-4-pmul.c | 8 ++
gcc/testsuite/gcc.target/aarch64/crc-5-pmul.c | 8 ++
gcc/testsuite/gcc.target/aarch64/crc-6-pmul.c | 8 ++
gcc/testsuite/gcc.target/aarch64/crc-7-pmul.c | 8 ++
gcc/testsuite/gcc.target/aarch64/crc-8-pmul.c | 8 ++
gcc/testsuite/gcc.target/aarch64/crc-9-pmul.c | 8 ++
.../gcc.target/aarch64/crc-CCIT-data16-pmul.c | 9 ++
.../gcc.target/aarch64/crc-CCIT-data8-pmul.c | 9 ++
.../aarch64/crc-coremark-16bitdata-pmul.c | 9 ++
.../gcc.target/aarch64/crc-crc32-data16.c | 53 +++++++
.../gcc.target/aarch64/crc-crc32-data32.c | 52 +++++++
.../gcc.target/aarch64/crc-crc32-data8.c | 53 +++++++
.../gcc.target/aarch64/crc-crc32c-data16.c | 53 +++++++
.../gcc.target/aarch64/crc-crc32c-data32.c | 52 +++++++
.../gcc.target/aarch64/crc-crc32c-data8.c | 53 +++++++
30 files changed, 668 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-1-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-10-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-12-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-13-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-14-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-17-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-18-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-21-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-22-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-23-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-4-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-5-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-6-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-7-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-8-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-9-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-CCIT-data16-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-CCIT-data8-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-coremark-16bitdata-pmul.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-crc32-data16.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-crc32-data32.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-crc32-data8.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-crc32c-data16.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-crc32c-data32.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/crc-crc32c-data8.c
@@ -1124,5 +1124,8 @@ extern void aarch64_adjust_reg_alloc_order ();
bool aarch64_optimize_mode_switching (aarch64_mode_entity);
void aarch64_restore_za (rtx);
+void aarch64_expand_crc_using_pmull (scalar_mode, scalar_mode, rtx *);
+void aarch64_expand_reversed_crc_using_pmull (scalar_mode, scalar_mode, rtx *);
+
#endif /* GCC_AARCH64_PROTOS_H */
@@ -4312,7 +4312,7 @@
;; RTL uses GCC vector extension indices throughout so flip only for assembly.
;; Extracting lane zero is split into a simple move when it is between SIMD
;; registers or a store.
-(define_insn_and_split "aarch64_get_lane<mode>"
+(define_insn_and_split "@aarch64_get_lane<mode>"
[(set (match_operand:<VEL> 0 "aarch64_simd_nonimmediate_operand" "=?r, w, Utv")
(vec_select:<VEL>
(match_operand:VALL_F16 1 "register_operand" "w, w, w")
@@ -30386,6 +30386,137 @@ aarch64_retrieve_sysreg (const char *regname, bool write_p, bool is128op)
return sysreg->encoding;
}
+/* Generate assembly to calculate CRC
+ using carry-less multiplication instruction.
+ OPERANDS[1] is input CRC,
+ OPERANDS[2] is data (message),
+ OPERANDS[3] is the polynomial without the leading 1. */
+
+void
+aarch64_expand_crc_using_pmull (scalar_mode crc_mode,
+ scalar_mode data_mode,
+ rtx *operands)
+{
+ /* Check and keep arguments. */
+ gcc_assert (!CONST_INT_P (operands[0]));
+ gcc_assert (CONST_INT_P (operands[3]));
+ rtx crc = operands[1];
+ rtx data = operands[2];
+ rtx polynomial = operands[3];
+
+ unsigned HOST_WIDE_INT crc_size = GET_MODE_BITSIZE (crc_mode);
+ unsigned HOST_WIDE_INT data_size = GET_MODE_BITSIZE (data_mode);
+ gcc_assert (crc_size <= 32);
+ gcc_assert (data_size <= crc_size);
+
+ /* Calculate the quotient. */
+ unsigned HOST_WIDE_INT
+ q = gf2n_poly_long_div_quotient (UINTVAL (polynomial), crc_size);
+ /* CRC calculation's main part. */
+ if (crc_size > data_size)
+ crc = expand_shift (RSHIFT_EXPR, DImode, crc, crc_size - data_size,
+ NULL_RTX, 1);
+
+ rtx t0 = force_reg (DImode, gen_int_mode (q, DImode));
+ polynomial = simplify_gen_unary (ZERO_EXTEND, DImode, polynomial,
+ GET_MODE (polynomial));
+ rtx t1 = force_reg (DImode, polynomial);
+
+ rtx a0 = expand_binop (DImode, xor_optab, crc, data, NULL_RTX, 1,
+ OPTAB_WIDEN);
+
+ rtx pmull_res = gen_reg_rtx (TImode);
+ emit_insn (gen_aarch64_crypto_pmulldi (pmull_res, a0, t0));
+ a0 = gen_lowpart (DImode, pmull_res);
+
+ a0 = expand_shift (RSHIFT_EXPR, DImode, a0, crc_size, NULL_RTX, 1);
+
+ emit_insn (gen_aarch64_crypto_pmulldi (pmull_res, a0, t1));
+ a0 = gen_lowpart (DImode, pmull_res);
+
+ if (crc_size > data_size)
+ {
+ rtx crc_part = expand_shift (LSHIFT_EXPR, DImode, operands[1], data_size,
+ NULL_RTX, 0);
+ a0 = expand_binop (DImode, xor_optab, a0, crc_part, NULL_RTX, 1,
+ OPTAB_DIRECT);
+ }
+
+ aarch64_emit_move (operands[0], gen_lowpart (crc_mode, a0));
+}
+
+/* Generate assembly to calculate reversed CRC
+ using carry-less multiplication instruction.
+ OPERANDS[1] is input CRC,
+ OPERANDS[2] is data,
+ OPERANDS[3] is the polynomial without the leading 1. */
+
+void
+aarch64_expand_reversed_crc_using_pmull (scalar_mode crc_mode,
+ scalar_mode data_mode,
+ rtx *operands)
+{
+ /* Check and keep arguments. */
+ gcc_assert (!CONST_INT_P (operands[0]));
+ gcc_assert (CONST_INT_P (operands[3]));
+ rtx crc = operands[1];
+ rtx data = operands[2];
+ rtx polynomial = operands[3];
+
+ unsigned HOST_WIDE_INT crc_size = GET_MODE_BITSIZE (crc_mode);
+ unsigned HOST_WIDE_INT data_size = GET_MODE_BITSIZE (data_mode);
+ gcc_assert (crc_size <= 32);
+ gcc_assert (data_size <= crc_size);
+
+ /* Calculate the quotient. */
+ unsigned HOST_WIDE_INT
+ q = gf2n_poly_long_div_quotient (UINTVAL (polynomial), crc_size);
+ /* Reflect the calculated quotient. */
+ q = reflect_hwi (q, crc_size + 1);
+ rtx t0 = force_reg (DImode, gen_int_mode (q, DImode));
+
+ /* Reflect the polynomial. */
+ unsigned HOST_WIDE_INT ref_polynomial = reflect_hwi (UINTVAL (polynomial),
+ crc_size);
+ /* An unshifted multiplier would require the final result to be extracted
+ using a shift right by DATA_SIZE - 1 bits. Shift the multiplier left
+ so that the shift right can be by CRC_SIZE bits instead. */
+ ref_polynomial <<= crc_size - data_size + 1;
+ rtx t1 = force_reg (DImode, gen_int_mode (ref_polynomial, DImode));
+
+ /* CRC calculation's main part. */
+ rtx a0 = expand_binop (DImode, xor_optab, crc, data, NULL_RTX, 1,
+ OPTAB_WIDEN);
+
+ /* Perform carry-less multiplication and get low part. */
+ rtx pmull_res = gen_reg_rtx (TImode);
+ emit_insn (gen_aarch64_crypto_pmulldi (pmull_res, a0, t0));
+ a0 = gen_lowpart (DImode, pmull_res);
+
+ a0 = expand_binop (DImode, and_optab, a0,
+ gen_int_mode (GET_MODE_MASK (data_mode), DImode),
+ NULL_RTX, 1, OPTAB_WIDEN);
+
+ /* Perform carry-less multiplication. */
+ emit_insn (gen_aarch64_crypto_pmulldi (pmull_res, a0, t1));
+
+ /* Perform a shift right by CRC_SIZE as an extraction of lane 1. */
+ machine_mode crc_vmode = aarch64_vq_mode (crc_mode).require ();
+ a0 = (crc_size > data_size ? gen_reg_rtx (crc_mode) : operands[0]);
+ emit_insn (gen_aarch64_get_lane (crc_vmode, a0,
+ gen_lowpart (crc_vmode, pmull_res),
+ aarch64_endian_lane_rtx (crc_vmode, 1)));
+
+ if (crc_size > data_size)
+ {
+ rtx crc_part = expand_shift (RSHIFT_EXPR, crc_mode, crc, data_size,
+ NULL_RTX, 1);
+ a0 = expand_binop (crc_mode, xor_optab, a0, crc_part, operands[0], 1,
+ OPTAB_WIDEN);
+ aarch64_emit_move (operands[0], a0);
+ }
+}
+
/* Target-specific selftests. */
#if CHECKING_P
@@ -4566,6 +4566,63 @@
[(set_attr "type" "crc")]
)
+;; Reversed CRC
+(define_expand "crc_rev<ALLI:mode><ALLX:mode>4"
+ [;; return value (calculated CRC)
+ (match_operand:ALLX 0 "register_operand" "=r")
+ ;; initial CRC
+ (match_operand:ALLX 1 "register_operand" "r")
+ ;; data
+ (match_operand:ALLI 2 "register_operand" "r")
+ ;; polynomial without leading 1
+ (match_operand:ALLX 3)]
+ ""
+ {
+ /* If the polynomial is the same as the polynomial of crc32c* instruction,
+ put that instruction. crc32c uses iSCSI polynomial. */
+ if (TARGET_CRC32 && INTVAL (operands[3]) == 0x1EDC6F41
+ && <ALLX:MODE>mode == SImode)
+ emit_insn (gen_aarch64_crc32c<ALLI:crc_data_type> (operands[0],
+ operands[1],
+ operands[2]));
+ /* If the polynomial is the same as the polynomial of crc32* instruction,
+ put that instruction. crc32 uses HDLC etc. polynomial. */
+ else if (TARGET_CRC32 && INTVAL (operands[3]) == 0x04C11DB7
+ && <ALLX:MODE>mode == SImode)
+ emit_insn (gen_aarch64_crc32<ALLI:crc_data_type> (operands[0],
+ operands[1],
+ operands[2]));
+ else if (TARGET_AES && <ALLI:sizen> <= <ALLX:sizen>)
+ aarch64_expand_reversed_crc_using_pmull (<ALLX:MODE>mode,
+ <ALLI:MODE>mode,
+ operands);
+ else
+ /* Otherwise, generate table-based CRC. */
+ expand_reversed_crc_table_based (operands[0], operands[1], operands[2],
+ operands[3], <ALLI:MODE>mode,
+ generate_reflecting_code_standard);
+ DONE;
+ }
+)
+
+;; Bit-forward CRC
+(define_expand "crc<ALLI:mode><ALLX:mode>4"
+ [;; return value (calculated CRC)
+ (match_operand:ALLX 0 "register_operand" "=r")
+ ;; initial CRC
+ (match_operand:ALLX 1 "register_operand" "r")
+ ;; data
+ (match_operand:ALLI 2 "register_operand" "r")
+ ;; polynomial without leading 1
+ (match_operand:ALLX 3)]
+ "TARGET_AES && <ALLI:sizen> <= <ALLX:sizen>"
+ {
+ aarch64_expand_crc_using_pmull (<ALLX:MODE>mode, <ALLI:MODE>mode,
+ operands);
+ DONE;
+ }
+)
+
(define_insn "*csinc2<mode>_insn"
[(set (match_operand:GPI 0 "register_operand" "=r")
(plus:GPI (match_operand 2 "aarch64_comparison_operation" "")
@@ -1280,6 +1280,10 @@
;; Map a mode to a specific constraint character.
(define_mode_attr cmode [(QI "q") (HI "h") (SI "s") (DI "d")])
+;; Map a mode to a specific constraint character for calling
+;; appropriate version of crc.
+(define_mode_attr crc_data_type [(QI "b") (HI "h") (SI "w") (DI "x")])
+
;; Map modes to Usg and Usj constraints for SISD right shifts
(define_mode_attr cmode_simd [(SI "g") (DI "j")])
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc -fdisable-tree-phiopt2 -fdisable-tree-phiopt3" } */
+
+#include "../../gcc.dg/torture/crc-1.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
\ No newline at end of file
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-10.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,9 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc -fdisable-tree-phiopt2 -fdisable-tree-phiopt3" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include "../../gcc.dg/torture/crc-12.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-13.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-14.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-17.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-18.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-21.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-22.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-23.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-4.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -w -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-5.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
\ No newline at end of file
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-6.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
\ No newline at end of file
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-7.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-8.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,8 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+
+#include "../../gcc.dg/torture/crc-9.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
new file mode 100644
@@ -0,0 +1,9 @@
+/* { dg-do run } */
+/* { dg-options "-w -march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include "../../gcc.dg/torture/crc-CCIT-data16.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
\ No newline at end of file
new file mode 100644
@@ -0,0 +1,9 @@
+/* { dg-do run } */
+/* { dg-options "-w -march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto" } } */
+
+#include "../../gcc.dg/torture/crc-CCIT-data8.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
\ No newline at end of file
new file mode 100644
@@ -0,0 +1,9 @@
+/* { dg-do run } */
+/* { dg-options "-w -march=armv8-a+crypto -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include "../../gcc.dg/torture/crc-coremark16-data16.c"
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "pmull" "dfinish"} } */
\ No newline at end of file
new file mode 100644
@@ -0,0 +1,53 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crc -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include <stdint.h>
+#include <stdlib.h>
+
+__attribute__ ((noinline,optimize(0)))
+uint32_t _crc32_O0 (uint32_t crc, uint16_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0xEDB88320;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+uint32_t _crc32 (uint32_t crc, uint16_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0xEDB88320;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+int main ()
+{
+ uint32_t crc = 0x0D800D80;
+ for (uint16_t i = 0; i < 0xffff; i++)
+ {
+ uint32_t res1 = _crc32_O0 (crc, i);
+ uint32_t res2 = _crc32 (crc, i);
+ if (res1 != res2)
+ abort ();
+ crc = res1;
+ }
+}
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "UNSPEC_CRC32" "dfinish"} } */
+/* { dg-final { scan-rtl-dump-times "pmull" 0 "dfinish"} } */
new file mode 100644
@@ -0,0 +1,52 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crc -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include <stdint.h>
+#include <stdlib.h>
+__attribute__ ((noinline,optimize(0)))
+uint32_t _crc32_O0 (uint32_t crc, uint32_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 32; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0xEDB88320;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+uint32_t _crc32 (uint32_t crc, uint32_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 32; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0xEDB88320;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+int main ()
+{
+ uint32_t crc = 0x0D800D80;
+ for (uint8_t i = 0; i < 0xff; i++)
+ {
+ uint32_t res1 = _crc32_O0 (crc, i);
+ uint32_t res2 = _crc32 (crc, i);
+ if (res1 != res2)
+ abort ();
+ crc = res1;
+ }
+}
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "UNSPEC_CRC32" "dfinish"} } */
+/* { dg-final { scan-rtl-dump-times "pmull" 0 "dfinish"} } */
new file mode 100644
@@ -0,0 +1,53 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crc -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include <stdint.h>
+#include <stdlib.h>
+
+__attribute__ ((noinline,optimize(0)))
+uint32_t _crc32_O0 (uint32_t crc, uint8_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0xEDB88320;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+uint32_t _crc32 (uint32_t crc, uint8_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0xEDB88320;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+int main ()
+{
+ uint32_t crc = 0x0D800D80;
+ for (uint8_t i = 0; i < 0xff; i++)
+ {
+ uint32_t res1 = _crc32_O0 (crc, i);
+ uint32_t res2 = _crc32 (crc, i);
+ if (res1 != res2)
+ abort ();
+ crc = res1;
+ }
+}
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "UNSPEC_CRC32" "dfinish"} } */
+/* { dg-final { scan-rtl-dump-times "pmull" 0 "dfinish"} } */
new file mode 100644
@@ -0,0 +1,53 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crc -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include <stdint.h>
+#include <stdlib.h>
+
+__attribute__ ((noinline,optimize(0)))
+uint32_t _crc32_O0 (uint32_t crc, uint16_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0x82F63B78;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+uint32_t _crc32 (uint32_t crc, uint16_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0x82F63B78;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+int main ()
+{
+ uint32_t crc = 0x0D800D80;
+ for (uint16_t i = 0; i < 0xffff; i++)
+ {
+ uint32_t res1 = _crc32_O0 (crc, i);
+ uint32_t res2 = _crc32 (crc, i);
+ if (res1 != res2)
+ abort ();
+ crc = res1;
+ }
+}
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "UNSPEC_CRC32C" "dfinish"} } */
+/* { dg-final { scan-rtl-dump-times "pmull" 0 "dfinish"} } */
new file mode 100644
@@ -0,0 +1,52 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crc -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include <stdint.h>
+#include <stdlib.h>
+__attribute__ ((noinline,optimize(0)))
+uint32_t _crc32_O0 (uint32_t crc, uint32_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 32; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0x82F63B78;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+uint32_t _crc32 (uint32_t crc, uint32_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 32; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0x82F63B78;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+int main ()
+{
+ uint32_t crc = 0x0D800D80;
+ for (uint8_t i = 0; i < 0xff; i++)
+ {
+ uint32_t res1 = _crc32_O0 (crc, i);
+ uint32_t res2 = _crc32 (crc, i);
+ if (res1 != res2)
+ abort ();
+ crc = res1;
+ }
+}
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "UNSPEC_CRC32C" "dfinish"} } */
+/* { dg-final { scan-rtl-dump-times "pmull" 0 "dfinish"} } */
new file mode 100644
@@ -0,0 +1,53 @@
+/* { dg-do run } */
+/* { dg-options "-march=armv8-a+crc -O2 -fdump-rtl-dfinish -fdump-tree-crc" } */
+/* { dg-skip-if "" { *-*-* } { "-flto"} } */
+
+#include <stdint.h>
+#include <stdlib.h>
+
+__attribute__ ((noinline,optimize(0)))
+uint32_t _crc32_O0 (uint32_t crc, uint8_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0x82F63B78;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+uint32_t _crc32 (uint32_t crc, uint8_t data) {
+ int i;
+ crc = crc ^ data;
+
+ for (i = 0; i < 8; i++) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ 0x82F63B78;
+ else
+ crc = (crc >> 1);
+ }
+
+ return crc;
+}
+
+int main ()
+{
+ uint32_t crc = 0x0D800D80;
+ for (uint8_t i = 0; i < 0xff; i++)
+ {
+ uint32_t res1 = _crc32_O0 (crc, i);
+ uint32_t res2 = _crc32 (crc, i);
+ if (res1 != res2)
+ abort ();
+ crc = res1;
+ }
+}
+
+/* { dg-final { scan-tree-dump "calculates CRC!" "crc"} } */
+/* { dg-final { scan-tree-dump-times "Couldn't generate faster CRC code." 0 "crc"} } */
+/* { dg-final { scan-rtl-dump "UNSPEC_CRC32C" "dfinish"} } */
+/* { dg-final { scan-rtl-dump-times "pmull" 0 "dfinish"} } */
--
2.25.1
This patch introduces two new expanders for the aarch64 backend, dedicated to generate optimized code for CRC computations. The new expanders are designed to leverage specific hardware capabilities to achieve faster CRC calculations, particularly using the crc32, crc32c and pmull instructions when supported by the target architecture. Expander 1: Bit-Forward CRC (crc<ALLI:mode><ALLX:mode>4) For targets that support pmul instruction (TARGET_AES), the expander will generate code that uses the pmull (crypto_pmulldi) instruction for CRC computation. Expander 2: Bit-Reversed CRC (crc_rev<ALLI:mode><ALLX:mode>4) The expander first checks if the target supports the CRC32* instruction set (TARGET_CRC32) and the polynomial in use is 0x1EDC6F41 (iSCSI) or 0x04C11DB7 (HDLC). If the conditions are met, it emits calls to the corresponding crc32* instruction (depending on the data size and the polynomial). If the target does not support crc32* but supports pmull, it then uses the pmull (crypto_pmulldi) instruction for bit-reversed CRC computation. Otherwise table-based CRC is generated. gcc/config/aarch64/ * aarch64-protos.h (aarch64_expand_crc_using_pmull): New extern function declaration. (aarch64_expand_reversed_crc_using_pmull): Likewise. * aarch64-simd.md (aarch64_get_lane<mode>): Rename to @aarch64_get_lane<mode>. * aarch64.cc (aarch64_expand_crc_using_pmull): New function. (aarch64_expand_reversed_crc_using_pmull): Likewise. * aarch64.md (crc_rev<ALLI:mode><ALLX:mode>4): New expander for reversed CRC. (crc<ALLI:mode><ALLX:mode>4): New expander for bit-forward CRC. * iterators.md (crc_data_type): New mode attribute. gcc/testsuite/gcc.target/aarch64/ * crc-1-pmul.c: New test. * crc-10-pmul.c: Likewise. * crc-12-pmul.c: Likewise. * crc-13-pmul.c: Likewise. * crc-14-pmul.c: Likewise. * crc-17-pmul.c: Likewise. * crc-18-pmul.c: Likewise. * crc-21-pmul.c: Likewise. * crc-22-pmul.c: Likewise. * crc-23-pmul.c: Likewise. * crc-4-pmul.c: Likewise. * crc-5-pmul.c: Likewise. * crc-6-pmul.c: Likewise. * crc-7-pmul.c: Likewise. * crc-8-pmul.c: Likewise. * crc-9-pmul.c: Likewise. * crc-CCIT-data16-pmul.c: Likewise. * crc-CCIT-data8-pmul.c: Likewise. * crc-coremark-16bitdata-pmul.c: Likewise. * crc-crc32-data16.c: Likewise. * crc-crc32-data32.c: Likewise. * crc-crc32-data8.c: Likewise. * crc-crc32c-data16.c: Likewise. * crc-crc32c-data32.c: Likewise. * crc-crc32c-data8.c: Likewise. Signed-off-by: Mariam Arutunian <mariamarutunian@gmail.com> Co-authored-by: Richard Sandiford <richard.sandiford@arm.com>