On Fri, Oct 9, 2026 at 5:09 PM Shreesh Adiga
<[email protected]> wrote:
>
>
>
> On Thu, Oct 8, 2026 at 10:25 PM Uros Bizjak <[email protected]> wrote:
>>
>> On Wed, Oct 7, 2026 at 5:28 PM Shreesh Adiga
>> <[email protected]> wrote:
>> >
>> > On Tue, Sep 8, 2026 at 3:46 PM Mariam Arutunian 
>> > <[email protected]> wrote:
>> >>
>> >> Thanks for the patch!
>> >>
>> >> I've had a quick look, and everything looks okay so far.
>> >
>> >
>> > Thanks Mariam for your review!
>> >
>> > GCC x86 maintainers: ping for review. Kindly assist with the next steps 
>> > for this change.
>> > I'm interested in working on 64-bit CRC expansion as a follow up once this 
>> > is merged.
>> >
>> > Thanks,
>> > Shreesh
>> >
>> >>
>> >> On Mon, Sep 7, 2026 at 1:56 PM Shreesh Adiga 
>> >> <[email protected]> wrote:
>> >>>
>> >>> From: Mariam Arutunian <[email protected]>
>> >>>
>> >>> This patch introduces pclmul expanders for the i386 backend,
>> >>> dedicated to generating optimized code for CRC computations.
>> >>>
>> >>> Expander 1: Bit-Forward CRC (crc<SWI1248x:mode><SWI124:mode>4)
>> >>> For targets that support both pclmulqdq instruction (TARGET_PCLMUL) and 
>> >>> are
>> >>> 64-bit (TARGET_64BIT),
>> >>> the expander will generate code that uses the pclmulqdq instruction for 
>> >>> CRC
>> >>> computation.
>> >>>
>> >>> Expander 2: Bit-Reversed CRC (crc_rev<SWI1248x:mode><SWI124:mode>4)
>> >>> If the target does not support crc32 but supports pclmulqdq, it then uses
>> >>> the pclmulqdq instruction for bit-reversed CRC computation.
>> >>>
>> >>> This makes the x86 backend similar to aarch64 which uses pmull.
>> >>> This is based on earlier submitted patch which was not merged for x86:
>> >>> https://gcc.gnu.org/pipermail/gcc-patches/2024-November/668248.html
>> >>>
>> >>> gcc/ChangeLog:
>> >>>
>> >>>         * config/i386/i386-expand.cc (ix86_expand_crc_using_pclmul): New
>> >>>         function that implements pclmul expansion for Bit-Forward CRC
>> >>>         computation.
>> >>>         (ix86_expand_reversed_crc_using_pclmul): New function that
>> >>>         implements pclmul expansion for Bit-Reversed CRC computation.
>> >>>         * config/i386/i386-protos.h (ix86_expand_crc_using_pclmul): New
>> >>>         extern function declaration.
>> >>>         (ix86_expand_reversed_crc_using_pclmul): Likewise.
>> >>>         * config/i386/i386.md (crc_rev<SWI124:mode>si4): Removed older
>> >>>         expansion for Bit-Reversed CRC.
>> >>>         (crc<SWI1248x:mode><SWI124:mode>4): Added new expander for
>> >>>         Bit-Forward CRC.
>> >>>         (crc_rev<SWI1248x:mode><SWI124:mode>4): Added new expander for
>> >>>         Bit-Reversed CRC which extends previous CRC32 expansion.
>> >>>
>> >>> gcc/testsuite/ChangeLog:
>> >>>
>> >>>         * gcc.target/i386/crc-1-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-10-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-12-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-13-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-14-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-17-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-18-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-21-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-22-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-23-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-4-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-5-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-6-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-7-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-8-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-9-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-CCIT-data16-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-CCIT-data8-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-coremark-16bitdata-pclmul.c: New test.
>> >>>         * gcc.target/i386/crc-crc32-data16.c: New test.
>> >>>         * gcc.target/i386/crc-crc32-data32.c: New test.
>> >>>         * gcc.target/i386/crc-crc32-data8.c: New test.
>> >>>
>> >>> Co-authored-by: Shreesh Adiga <[email protected]>
>> >>> Signed-off-by: Shreesh Adiga <[email protected]>
>>
>> Mariam's signoff is needed here.
>>
>> >>> ---
>> >>>  gcc/config/i386/i386-expand.cc                | 133 ++++++++++++++++++
>> >>>  gcc/config/i386/i386-protos.h                 |   3 +
>> >>>  gcc/config/i386/i386.md                       |  53 +++++--
>> >>>  gcc/testsuite/gcc.target/i386/crc-1-pclmul.c  |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-10-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-12-pclmul.c |   9 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-13-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-14-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-17-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-18-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-21-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-22-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-23-pclmul.c |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-4-pclmul.c  |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-5-pclmul.c  |   9 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-6-pclmul.c  |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-7-pclmul.c  |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-8-pclmul.c  |   8 ++
>> >>>  gcc/testsuite/gcc.target/i386/crc-9-pclmul.c  |   8 ++
>> >>>  .../gcc.target/i386/crc-CCIT-data16-pclmul.c  |   9 ++
>> >>>  .../gcc.target/i386/crc-CCIT-data8-pclmul.c   |   9 ++
>> >>>  .../i386/crc-coremark-16bitdata-pclmul.c      |   9 ++
>> >>>  .../gcc.target/i386/crc-crc32-data16.c        |  53 +++++++
>> >>>  .../gcc.target/i386/crc-crc32-data32.c        |  53 +++++++
>> >>>  .../gcc.target/i386/crc-crc32-data8.c         |  53 +++++++
>> >>>  25 files changed, 492 insertions(+), 13 deletions(-)
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-1-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-10-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-12-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-13-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-14-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-17-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-18-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-21-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-22-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-23-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-4-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-5-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-6-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-7-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-8-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-9-pclmul.c
>> >>>  create mode 100644 
>> >>> gcc/testsuite/gcc.target/i386/crc-CCIT-data16-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-CCIT-data8-pclmul.c
>> >>>  create mode 100644 
>> >>> gcc/testsuite/gcc.target/i386/crc-coremark-16bitdata-pclmul.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-crc32-data16.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-crc32-data32.c
>> >>>  create mode 100644 gcc/testsuite/gcc.target/i386/crc-crc32-data8.c
>> >>>
>> >>> diff --git a/gcc/config/i386/i386-expand.cc 
>> >>> b/gcc/config/i386/i386-expand.cc
>> >>> index fb4224af0da..6010892e3dc 100644
>> >>> --- a/gcc/config/i386/i386-expand.cc
>> >>> +++ b/gcc/config/i386/i386-expand.cc
>> >>> @@ -29917,4 +29917,137 @@ ix86_expand_lcp_stall_peephole (rtx_insn 
>> >>> *insn, rtx *operands,
>> >>>    emit_insn (set);
>> >>>  }
>> >>>
>> >>> +/* Generate assembly to calculate CRC using pclmulqdq instruction.
>> >>> +   OPERANDS[1] is input CRC,
>> >>> +   OPERANDS[2] is data (message),
>> >>> +   OPERANDS[3] is the polynomial without the leading 1.  */
>> >>> +
>> >>> +void
>> >>> +ix86_expand_crc_using_pclmul (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);
>> >>> +
>> >>> +  if (crc_size > data_size)
>> >>> +    crc = expand_shift (RSHIFT_EXPR, DImode, crc, crc_size - data_size,
>> >>> +                       NULL_RTX, 1);
>> >>> +
>> >>> +  /* Keep the quotient in V2DImode.  */
>> >>> +  rtx q_v2di = gen_reg_rtx (V2DImode);
>> >>> +  rtx quotient = force_reg (DImode, gen_int_mode (q, DImode));
>> >>> +  emit_insn (gen_vec_concatv2di (q_v2di, quotient, const0_rtx));
>>
>> This will move the constant through GPR and will result in movabs (a
>> costly insn) and inter-unit movq. It is probably cheaper to have a
>> DImode constant in the constant pool and movq it from there. I assume
>> the compiler will move the memory load out of the loop by itself.
>>
>> >>> +  /* crc ^ data and keep in V2DImode.  */
>> >>> +  rtx cd_xor = expand_binop (DImode, xor_optab, crc, data, NULL_RTX, 1,
>> >>> +                            OPTAB_WIDEN);
>> >>> +
>> >>> +  rtx res = gen_reg_rtx (V2DImode);
>> >>> +  emit_insn (gen_vec_concatv2di (res, cd_xor, const0_rtx));
>> >>> +  /* Perform carry-less multiplication.  */
>> >>> +  emit_insn (gen_pclmulqdq (res, res, q_v2di, gen_int_mode (0, 
>> >>> SImode)));
>>
>> const0_rtx
>>
>> >>> +
>> >>> +  res = expand_shift (RSHIFT_EXPR, V2DImode, res, crc_size, NULL_RTX, 
>> >>> 1);
>> >>> +
>> >>> +  /* Keep the polynomial in V2DImode.  */
>> >>> +  polynomial = simplify_gen_unary (ZERO_EXTEND, DImode, polynomial,
>> >>> +                                  GET_MODE (polynomial));
>> >>> +  rtx t1 = force_reg (DImode, polynomial);
>> >>> +  rtx p_v2di = gen_reg_rtx (V2DImode);
>> >>> +  emit_insn (gen_vec_concatv2di (p_v2di, t1, const0_rtx));
>>
>> Here you should use movd from memory (sse2_loadld + some subreg magic).
>>
>
> Sure I have been looking into the review suggestions and have made the 
> changes locally.
> I just wanted to confirm if doing movq (quotient) + clmul + movd (polynomial) 
> + clmul is better than doing
> movdqa (quotient, polynomial) + clmul + clmul with different selector 
> argument instead of 0.
> Could you share your views on whether clubbing the two constants into a 
> single XMM register load and
> performing clmul with different lanes would be better or not?

I don’t have performance data for this, and as the proposer it’s your
job to benchmark the alternatives. My expectation is that a single
16-byte load with different clmul selectors is no worse than movq +
movd (fewer uops, no GPR→XMM move), but please verify. Agner Fog’s
tables [1] are a good start, and uiCA/llvm-mca can help with
estimates. Please post measured numbers from at least Intel and AMD
with the next revision.

[1] https://www.agner.org/optimize/

Uros.

>
> Thanks,
> Shreesh
>
>> >>> +
>> >>> +  /* Perform carry-less multiplication and get low part.  */
>> >>> +  emit_insn (gen_pclmulqdq (res, res, p_v2di, gen_int_mode (0, 
>> >>> SImode)));
>> >>> +  rtx crc_part = gen_reg_rtx (DImode);
>> >>> +  emit_insn (gen_vec_extractv2didi (crc_part, res, const0_rtx));
>> >>> +
>> >>> +  if (crc_size > data_size)
>> >>> +    {
>> >>> +      rtx shift = expand_shift (LSHIFT_EXPR, DImode, operands[1], 
>> >>> data_size,
>> >>> +                               NULL_RTX, 1);
>> >>> +      crc_part = expand_binop (DImode, xor_optab, crc_part, shift, 
>> >>> NULL_RTX, 1,
>> >>> +                              OPTAB_DIRECT);
>> >>> +    }
>> >>> +  emit_move_insn (operands[0], gen_lowpart (crc_mode, crc_part));
>> >>> +}
>> >>> +
>> >>> +/* Generate assembly to calculate reversed CRC using pclmulqdq 
>> >>> instruction.
>> >>> +   OPERANDS[1] is input CRC,
>> >>> +   OPERANDS[2] is data (message),
>> >>> +   OPERANDS[3] is the polynomial without the leading 1.  */
>> >>> +
>> >>> +void
>> >>> +ix86_expand_reversed_crc_using_pclmul (scalar_mode crc_mode,
>> >>> +                                      scalar_mode data_mode,
>> >>> +                                      rtx *operands)
>>
>> The same comments as above apply to this function, too.
>>
>> >>> +{
>> >>> +  /* 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 q_v2di = gen_reg_rtx (V2DImode);
>> >>> +  rtx quotient = force_reg (DImode, gen_int_mode (q, DImode));
>> >>> +  emit_insn (gen_vec_concatv2di (q_v2di, quotient, const0_rtx));
>> >>> +
>> >>> +  /* crc ^ data and keep in V2DImode.  */
>> >>> +  rtx cd_xor = expand_binop (DImode, xor_optab, crc, data, NULL_RTX, 1,
>> >>> +                            OPTAB_WIDEN);
>> >>> +
>> >>> +  /* Perform carry-less multiplication.  */
>> >>> +  rtx res = gen_reg_rtx (V2DImode);
>> >>> +  emit_insn (gen_vec_concatv2di (res, cd_xor, const0_rtx));
>> >>> +  emit_insn (gen_pclmulqdq (res, res, q_v2di, gen_int_mode (0, 
>> >>> SImode)));
>> >>> +
>> >>> +  res = expand_shift (LSHIFT_EXPR, V2DImode, res, 64 - data_size, 
>> >>> NULL_RTX, 0);
>> >>> +
>> >>> +  /* Reflect the polynomial and keep in V2DImode.  */
>> >>> +  unsigned HOST_WIDE_INT reflected_op3 = reflect_hwi (UINTVAL 
>> >>> (polynomial),
>> >>> +                                                     crc_size);
>> >>> +  rtx ref_polynomial = force_reg (DImode,
>> >>> +                                 gen_int_mode (reflected_op3 << 1, 
>> >>> DImode));
>> >>> +  rtx p_v2di = gen_reg_rtx (V2DImode);
>> >>> +  emit_insn (gen_vec_concatv2di (p_v2di, ref_polynomial, const0_rtx));
>> >>> +
>> >>> +  /* Perform carry-less multiplication and get high part.  */
>> >>> +  emit_insn (gen_pclmulqdq (res, res, p_v2di, gen_int_mode (0, 
>> >>> SImode)));
>> >>> +  rtx res_high = gen_reg_rtx (DImode);
>> >>> +  emit_insn (gen_vec_extractv2didi (res_high, res, const1_rtx));
>> >>> +
>> >>> +  if (crc_size > data_size)
>> >>> +    {
>> >>> +      rtx shift = expand_shift (RSHIFT_EXPR, DImode, crc, data_size,
>> >>> +                               NULL_RTX, 1);
>> >>> +      res_high = expand_binop (DImode, xor_optab, res_high, shift, 
>> >>> NULL_RTX, 1,
>> >>> +                              OPTAB_DIRECT);
>> >>> +    }
>> >>> +  emit_move_insn (operands[0], gen_lowpart (crc_mode, res_high));
>> >>> +}
>> >>> +
>> >>>  #include "gt-i386-expand.h"
>> >>> diff --git a/gcc/config/i386/i386-protos.h 
>> >>> b/gcc/config/i386/i386-protos.h
>> >>> index 21994d3d498..d225a8fadc2 100644
>> >>> --- a/gcc/config/i386/i386-protos.h
>> >>> +++ b/gcc/config/i386/i386-protos.h
>> >>> @@ -449,3 +449,6 @@ extern void ix86_set_handled_components (sbitmap);
>> >>>  bool ix86_check_builtin_isa_match (unsigned int, HOST_WIDE_INT*,
>> >>>                                    HOST_WIDE_INT*);
>> >>>  rtx ix86_vgf2p8affine_shift_matrix (rtx, rtx, enum rtx_code);
>> >>> +extern void ix86_expand_crc_using_pclmul (scalar_mode, scalar_mode, rtx 
>> >>> *);
>> >>> +extern void ix86_expand_reversed_crc_using_pclmul (scalar_mode, 
>> >>> scalar_mode,
>> >>> +                                                  rtx *);
>> >>> diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
>> >>> index 4e18797743f..7538b1f70f1 100644
>> >>> --- a/gcc/config/i386/i386.md
>> >>> +++ b/gcc/config/i386/i386.md
>> >>> @@ -30504,19 +30504,46 @@ (define_insn "sse4_2_crc32di"
>> >>>     (set_attr "prefix_extra" "1")
>> >>>     (set_attr "mode" "DI")])
>> >>>
>> >>> -(define_expand "crc_rev<SWI124:mode>si4"
>> >>> -  [(match_operand:SI 0 "register_operand")
>> >>> -   (match_operand:SI 1 "register_operand")
>> >>> -   (match_operand:SWI124 2 "nonimmediate_operand")
>> >>> -   (match_operand:SI 3 "const_int_operand")]
>> >>> -  "TARGET_CRC32"
>> >>> -{
>> >>> -  /* crc32 uses iSCSI polynomial */
>> >>> -  if (INTVAL (operands[3]) == 0x1EDC6F41)
>> >>> -    emit_insn (gen_sse4_2_crc32<mode> (operands[0], operands[1], 
>> >>> operands[2]));
>> >>> -  else
>> >>> -    expand_reversed_crc_table_based (operands[0], operands[1], 
>> >>> operands[2],
>> >>> -                                    operands[3], <SWI124:MODE>mode);
>> >>> +;; Bit-forward CRC
>> >>> +(define_expand "crc<SWI1248x:mode><SWI124:mode>4"
>> >>> +  [;; return value (calculated CRC)
>> >>> +   (match_operand:SWI124 0 "register_operand" "=r")
>> >>> +   ;; initial CRC
>> >>> +   (match_operand:SWI124 1 "register_operand" "r")
>> >>> +   ;; data
>> >>> +   (match_operand:SWI1248x 2 "register_operand" "r")
>>
>> Please remove constraints, they are ignored in expanders. Also, please
>> place comments after operands, see e.g. atomic_compare_and_swap<mode>.
>>
>> >>> +   ;; polynomial without leading 1
>> >>> +   (match_operand:SWI124 3 "const_int_operand")]
>> >>> +  "TARGET_PCLMUL && TARGET_64BIT && <SWI124:MODE>mode >= 
>> >>> <SWI1248x:MODE>mode"
>>
>> Please write:
>>
>> TARGET_64BIT && TARGET_PCLMUL
>> && <SWI124...
>>
>> Please mind the line length limit.
>>
>> >>> +{
>> >>> +   ix86_expand_crc_using_pclmul (<SWI124:MODE>mode, <SWI1248x:MODE>mode,
>> >>> +                                operands);
>> >>> +   DONE;
>> >>> +})
>> >>> +
>> >>> +;; Reversed CRC
>> >>> +(define_expand "crc_rev<SWI1248x:mode><SWI124:mode>4"
>> >>> +  [;; return value (calculated CRC)
>> >>> +   (match_operand:SWI124 0 "register_operand" "=r")
>> >>> +   ;; initial CRC
>> >>> +   (match_operand:SWI124 1 "register_operand" "r")
>> >>> +   ;; data
>> >>> +   (match_operand:SWI1248x 2 "register_operand" "r")
>> >>> +   ;; polynomial without leading 1
>> >>> +   (match_operand:SWI124 3 "const_int_operand")]
>>
>> Same here.
>>
>> >>> +  "<SWI124:MODE>mode >= <SWI1248x:MODE>mode"
>> >>> +  {
>> >>> +    /* If it is iSCSI polynomial (0x1EDC6F41), generate crc32 
>> >>> instruction.  */
>> >>> +    if (TARGET_CRC32 && INTVAL (operands[3]) == 0x1EDC6F41
>> >>> +       && <SWI124:MODE>mode == SImode)
>> >>> +      emit_insn (gen_sse4_2_crc32<SWI1248x:mode> (operands[0], 
>> >>> operands[1],
>> >>> +                                                 operands[2]));
>> >>> +    else if (TARGET_PCLMUL && TARGET_64BIT)
>> >>> +      ix86_expand_reversed_crc_using_pclmul (<SWI124:MODE>mode,
>> >>> +                                            <SWI1248x:MODE>mode, 
>> >>> operands);
>> >>> +    else
>> >>> +      expand_reversed_crc_table_based (operands[0], operands[1], 
>> >>> operands[2],
>> >>> +                                      operands[3], <SWI1248x:MODE>mode);
>> >>>    DONE;
>> >>>  })
>> >>>
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-1-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-1-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..21edf417f0c
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-1-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> \ No newline at end of file
>>
>> Please put a newline here, also in other test files.
>>
>> Uros.
>>
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-10-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-10-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..39bfd386d9c
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-10-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-12-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-12-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..1ac9a6bf56d
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-12-pclmul.c
>> >>> @@ -0,0 +1,9 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-13-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-13-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..c290539fad3
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-13-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-14-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-14-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..cc62ee471c7
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-14-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-17-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-17-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..660bff55e1b
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-17-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-18-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-18-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..e54392b32a9
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-18-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-21-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-21-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..4db1504cd49
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-21-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-22-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-22-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..d0f27d96069
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-22-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-23-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-23-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..666f3620597
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-23-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-4-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-4-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..398ecaa4aba
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-4-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-5-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-5-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..b80368e81bc
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-5-pclmul.c
>> >>> @@ -0,0 +1,9 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -O2 -w -fdump-rtl-dfinish -fdump-tree-crc" } 
>> >>> */
>> >>> +/* { dg-skip-if "" { *-*-* } { "-flto"} } */
>> >>> +
>> >>> +#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 "pclmulqdq" "dfinish"} } */
>> >>> \ No newline at end of file
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-6-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-6-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..20b851e3596
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-6-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> \ No newline at end of file
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-7-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-7-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..3e5cc75338e
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-7-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-8-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-8-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..4b1145553fc
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-8-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-9-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-9-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..204d6c84d47
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-9-pclmul.c
>> >>> @@ -0,0 +1,8 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-CCIT-data16-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-CCIT-data16-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..ca728120858
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-CCIT-data16-pclmul.c
>> >>> @@ -0,0 +1,9 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-w -mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> \ No newline at end of file
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-CCIT-data8-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-CCIT-data8-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..816e0561d8f
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-CCIT-data8-pclmul.c
>> >>> @@ -0,0 +1,9 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-w -mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> \ No newline at end of file
>> >>> diff --git 
>> >>> a/gcc/testsuite/gcc.target/i386/crc-coremark-16bitdata-pclmul.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-coremark-16bitdata-pclmul.c
>> >>> new file mode 100644
>> >>> index 00000000000..817d960b0aa
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-coremark-16bitdata-pclmul.c
>> >>> @@ -0,0 +1,9 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-w -mpclmul -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 "pclmulqdq" "dfinish"} } */
>> >>> \ No newline at end of file
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-crc32-data16.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-crc32-data16.c
>> >>> new file mode 100644
>> >>> index 00000000000..49ab5f31ef0
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-crc32-data16.c
>> >>> @@ -0,0 +1,53 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mcrc32 -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_CRC32" "dfinish"} } */
>> >>> +/* { dg-final { scan-rtl-dump-times "pclmulqdq" 0 "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-crc32-data32.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-crc32-data32.c
>> >>> new file mode 100644
>> >>> index 00000000000..08d6c193a77
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-crc32-data32.c
>> >>> @@ -0,0 +1,53 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mcrc32 -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_CRC32" "dfinish"} } */
>> >>> +/* { dg-final { scan-rtl-dump-times "pclmulqdq" 0 "dfinish"} } */
>> >>> diff --git a/gcc/testsuite/gcc.target/i386/crc-crc32-data8.c 
>> >>> b/gcc/testsuite/gcc.target/i386/crc-crc32-data8.c
>> >>> new file mode 100644
>> >>> index 00000000000..7a76b27fd28
>> >>> --- /dev/null
>> >>> +++ b/gcc/testsuite/gcc.target/i386/crc-crc32-data8.c
>> >>> @@ -0,0 +1,53 @@
>> >>> +/* { dg-do run } */
>> >>> +/* { dg-options "-mcrc32 -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_CRC32" "dfinish"} } */
>> >>> +/* { dg-final { scan-rtl-dump-times "pclmulqdq" 0 "dfinish"} } */
>> >>> --
>> >>> 2.55.0
>> >>>

Reply via email to