On Fri, Sep 16, 2022 at 2:55 AM liuhongt via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> For ifloor/lfloor/iceil/lceil/irint/lrint/iround/lround when size of
> in_mode is not equal out_mode, vectorizer doesn't go to internal fn
> way,still left that part in the ix86_builtin_vectorized_function.
>
> Remove others builtins and add corresponding expanders.
> Note the patch just refactor the codes, doesn't solve the related case
> in the PR which needs extra expander for 64-bit vector.
>
> Bootstrapped and regtested on x86-64-pc-linux-gnu{-m32,}.
> Ok for trunk.
>
> gcc/ChangeLog:
>
> PR target/106910
> * config/i386/i386-builtins.cc
> (ix86_builtin_vectorized_function): Modernized with
> corresponding expanders.
> * config/i386/sse.md (lrint<mode><sseintvecmodelower>2): New
> expander.
> (floor<mode>2): Ditto.
> (lfloor<mode><sseintvecmodelower>2): Ditto.
> (ceil<mode>2): Ditto.
> (lceil<mode><sseintvecmodelower>2): Ditto.
> (btrunc<mode>2): Ditto.
> (lround<mode><sseintvecmodelower>2): Ditto.
> (exp2<mode>2): Ditto.
LGTM.
Thanks,
Uros.
> ---
> gcc/config/i386/i386-builtins.cc | 185 +------------------------------
> gcc/config/i386/sse.md | 80 +++++++++++++
> 2 files changed, 84 insertions(+), 181 deletions(-)
>
> diff --git a/gcc/config/i386/i386-builtins.cc
> b/gcc/config/i386/i386-builtins.cc
> index 6a04fb57e65..af2faee245b 100644
> --- a/gcc/config/i386/i386-builtins.cc
> +++ b/gcc/config/i386/i386-builtins.cc
> @@ -1540,21 +1540,16 @@ ix86_builtin_vectorized_function (unsigned int fn,
> tree type_out,
>
> switch (fn)
> {
> - CASE_CFN_EXP2:
> - if (out_mode == SFmode && in_mode == SFmode)
> - {
> - if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_EXP2PS);
> - }
> - break;
> -
> CASE_CFN_IFLOOR:
> CASE_CFN_LFLOOR:
> - CASE_CFN_LLFLOOR:
> /* The round insn does not trap on denormals. */
> if (flag_trapping_math || !TARGET_SSE4_1)
> break;
>
> + /* PR106910, currently vectorizer doesn't go direct internal fn way
> + when out_n != in_n, so let's still keep this.
> + Otherwise, it relies on expander of
> + lceilmn2/lfloormn2/lroundmn2/lrintmn2. */
> if (out_mode == SImode && in_mode == DFmode)
> {
> if (out_n == 4 && in_n == 2)
> @@ -1564,20 +1559,10 @@ ix86_builtin_vectorized_function (unsigned int fn,
> tree type_out,
> else if (out_n == 16 && in_n == 8)
> return ix86_get_builtin (IX86_BUILTIN_FLOORPD_VEC_PACK_SFIX512);
> }
> - if (out_mode == SImode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPS_SFIX);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPS_SFIX256);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPS_SFIX512);
> - }
> break;
>
> CASE_CFN_ICEIL:
> CASE_CFN_LCEIL:
> - CASE_CFN_LLCEIL:
> /* The round insn does not trap on denormals. */
> if (flag_trapping_math || !TARGET_SSE4_1)
> break;
> @@ -1591,20 +1576,10 @@ ix86_builtin_vectorized_function (unsigned int fn,
> tree type_out,
> else if (out_n == 16 && in_n == 8)
> return ix86_get_builtin (IX86_BUILTIN_CEILPD_VEC_PACK_SFIX512);
> }
> - if (out_mode == SImode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPS_SFIX);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPS_SFIX256);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPS_SFIX512);
> - }
> break;
>
> CASE_CFN_IRINT:
> CASE_CFN_LRINT:
> - CASE_CFN_LLRINT:
> if (out_mode == SImode && in_mode == DFmode)
> {
> if (out_n == 4 && in_n == 2)
> @@ -1614,20 +1589,10 @@ ix86_builtin_vectorized_function (unsigned int fn,
> tree type_out,
> else if (out_n == 16 && in_n == 8)
> return ix86_get_builtin (IX86_BUILTIN_VEC_PACK_SFIX512);
> }
> - if (out_mode == SImode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_CVTPS2DQ);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_CVTPS2DQ256);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_CVTPS2DQ512);
> - }
> break;
>
> CASE_CFN_IROUND:
> CASE_CFN_LROUND:
> - CASE_CFN_LLROUND:
> /* The round insn does not trap on denormals. */
> if (flag_trapping_math || !TARGET_SSE4_1)
> break;
> @@ -1641,150 +1606,8 @@ ix86_builtin_vectorized_function (unsigned int fn,
> tree type_out,
> else if (out_n == 16 && in_n == 8)
> return ix86_get_builtin
> (IX86_BUILTIN_ROUNDPD_AZ_VEC_PACK_SFIX512);
> }
> - if (out_mode == SImode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_ROUNDPS_AZ_SFIX);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_ROUNDPS_AZ_SFIX256);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_ROUNDPS_AZ_SFIX512);
> - }
> break;
>
> - CASE_CFN_FLOOR:
> - /* The round insn does not trap on denormals. */
> - if (flag_trapping_math || !TARGET_SSE4_1)
> - break;
> -
> - if (out_mode == DFmode && in_mode == DFmode)
> - {
> - if (out_n == 2 && in_n == 2)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPD);
> - else if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPD256);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPD512);
> - }
> - if (out_mode == SFmode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPS);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPS256);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPS512);
> - }
> - if (out_mode == HFmode && in_mode == HFmode)
> - {
> - /* V8HF/V16HF is supported in ix86_vector_mode_supported_p
> - under TARGET_AVX512FP16, TARGET_AVX512VL is needed here. */
> - if (out_n < 32 && !TARGET_AVX512VL)
> - break;
> -
> - if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPH);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPH256);
> - else if (out_n == 32 && in_n == 32)
> - return ix86_get_builtin (IX86_BUILTIN_FLOORPH512);
> - }
> - break;
> -
> - CASE_CFN_CEIL:
> - /* The round insn does not trap on denormals. */
> - if (flag_trapping_math || !TARGET_SSE4_1)
> - break;
> -
> - if (out_mode == DFmode && in_mode == DFmode)
> - {
> - if (out_n == 2 && in_n == 2)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPD);
> - else if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPD256);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPD512);
> - }
> - if (out_mode == SFmode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPS);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPS256);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPS512);
> - }
> - if (out_mode == HFmode && in_mode == HFmode)
> - {
> - /* V8HF/V16HF is supported in ix86_vector_mode_supported_p
> - under TARGET_AVX512FP16, TARGET_AVX512VL is needed here. */
> - if (out_n < 32 && !TARGET_AVX512VL)
> - break;
> -
> - if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPH);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPH256);
> - else if (out_n == 32 && in_n == 32)
> - return ix86_get_builtin (IX86_BUILTIN_CEILPH512);
> - }
> - break;
> -
> - CASE_CFN_TRUNC:
> - /* The round insn does not trap on denormals. */
> - if (flag_trapping_math || !TARGET_SSE4_1)
> - break;
> -
> - if (out_mode == DFmode && in_mode == DFmode)
> - {
> - if (out_n == 2 && in_n == 2)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPD);
> - else if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPD256);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPD512);
> - }
> - if (out_mode == SFmode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPS);
> - else if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPS256);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPS512);
> - }
> - if (out_mode == HFmode && in_mode == HFmode)
> - {
> - /* V8HF/V16HF is supported in ix86_vector_mode_supported_p
> - under TARGET_AVX512FP16, TARGET_AVX512VL is needed here. */
> - if (out_n < 32 && !TARGET_AVX512VL)
> - break;
> -
> - if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPH);
> - else if (out_n == 16 && in_n == 16)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPH256);
> - else if (out_n == 32 && in_n == 32)
> - return ix86_get_builtin (IX86_BUILTIN_TRUNCPH512);
> - }
> - break;
> -
> - CASE_CFN_FMA:
> - if (out_mode == DFmode && in_mode == DFmode)
> - {
> - if (out_n == 2 && in_n == 2)
> - return ix86_get_builtin (IX86_BUILTIN_VFMADDPD);
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_VFMADDPD256);
> - }
> - if (out_mode == SFmode && in_mode == SFmode)
> - {
> - if (out_n == 4 && in_n == 4)
> - return ix86_get_builtin (IX86_BUILTIN_VFMADDPS);
> - if (out_n == 8 && in_n == 8)
> - return ix86_get_builtin (IX86_BUILTIN_VFMADDPS256);
> - }
> - break;
>
> default:
> break;
> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> index d535c0af043..dd6c94dce05 100644
> --- a/gcc/config/i386/sse.md
> +++ b/gcc/config/i386/sse.md
> @@ -321,6 +321,11 @@ (define_mode_iterator VF
> [(V16SF "TARGET_AVX512F") (V8SF "TARGET_AVX") V4SF
> (V8DF "TARGET_AVX512F") (V4DF "TARGET_AVX") (V2DF "TARGET_SSE2")])
>
> +(define_mode_iterator VF1_VF2_AVX512DQ
> + [(V16SF "TARGET_AVX512F") (V8SF "TARGET_AVX") V4SF
> + (V8DF "TARGET_AVX512DQ") (V4DF "TARGET_AVX512DQ && TARGET_AVX512VL")
> + (V2DF "TARGET_AVX512DQ && TARGET_AVX512VL")])
> +
> (define_mode_iterator VFH
> [(V32HF "TARGET_AVX512FP16")
> (V16HF "TARGET_AVX512FP16 && TARGET_AVX512VL")
> @@ -23177,6 +23182,14 @@ (define_expand "rint<mode>2"
> "TARGET_SSE4_1"
> "operands[2] = GEN_INT (ROUND_MXCSR);")
>
> +;; Note vcvtpd2qq require avx512dq for all vector lengths.
> +(define_expand "lrint<mode><sseintvecmodelower>2"
> + [(set (match_operand:<sseintvecmode> 0 "register_operand")
> + (unspec:<sseintvecmode>
> + [(match_operand:VF1_VF2_AVX512DQ 1 "register_operand")]
> + UNSPEC_FIX_NOTRUNC))]
> + "TARGET_SSE2")
> +
> (define_insn "<sse4_1>_round<ssemodesuffix><avxsizesuffix>"
> [(set (match_operand:VF_128_256 0 "register_operand" "=Yr,*x,x")
> (unspec:VF_128_256
> @@ -23316,6 +23329,55 @@ (define_insn "*sse4_1_round<ssescalarmodesuffix>"
> (set_attr "prefix" "orig,orig,vex,evex")
> (set_attr "mode" "<MODE>")])
>
> +(define_expand "floor<mode>2"
> + [(set (match_operand:VFH 0 "register_operand")
> + (unspec:VFH
> + [(match_operand:VFH 1 "vector_operand")
> + (match_dup 2)]
> + UNSPEC_ROUND))]
> + "TARGET_SSE4_1 && !flag_trapping_math"
> + "operands[2] = GEN_INT (ROUND_FLOOR);")
> +
> +(define_expand "lfloor<mode><sseintvecmodelower>2"
> + [(match_operand:<sseintvecmode> 0 "register_operand")
> + (match_operand:VF1_VF2_AVX512DQ 1 "register_operand")]
> + "TARGET_SSE4_1 && !flag_trapping_math"
> +{
> + rtx tmp = gen_reg_rtx (<MODE>mode);
> + emit_insn (gen_floor<mode>2 (tmp, operands[1]));
> + emit_insn (gen_fix_trunc<mode><sseintvecmodelower>2 (operands[0], tmp));
> + DONE;
> +})
> +
> +(define_expand "ceil<mode>2"
> + [(set (match_operand:VFH 0 "register_operand")
> + (unspec:VFH
> + [(match_operand:VFH 1 "vector_operand")
> + (match_dup 2)]
> + UNSPEC_ROUND))]
> + "TARGET_SSE4_1 && !flag_trapping_math"
> + "operands[2] = GEN_INT (ROUND_CEIL);")
> +
> +(define_expand "lceil<mode><sseintvecmodelower>2"
> + [(match_operand:<sseintvecmode> 0 "register_operand")
> + (match_operand:VF1_VF2_AVX512DQ 1 "register_operand")]
> + "TARGET_SSE4_1 && !flag_trapping_math"
> +{
> + rtx tmp = gen_reg_rtx (<MODE>mode);
> + emit_insn (gen_ceil<mode>2 (tmp, operands[1]));
> + emit_insn (gen_fix_trunc<mode><sseintvecmodelower>2 (operands[0], tmp));
> + DONE;
> +})
> +
> +(define_expand "btrunc<mode>2"
> + [(set (match_operand:VFH 0 "register_operand")
> + (unspec:VFH
> + [(match_operand:VFH 1 "vector_operand")
> + (match_dup 2)]
> + UNSPEC_ROUND))]
> + "TARGET_SSE4_1 && !flag_trapping_math"
> + "operands[2] = GEN_INT (ROUND_TRUNC);")
> +
> (define_expand "round<mode>2"
> [(set (match_dup 3)
> (plus:VF
> @@ -23350,6 +23412,17 @@ (define_expand "round<mode>2"
> operands[4] = GEN_INT (ROUND_TRUNC);
> })
>
> +(define_expand "lround<mode><sseintvecmodelower>2"
> + [(match_operand:<sseintvecmode> 0 "register_operand")
> + (match_operand:VF1_VF2_AVX512DQ 1 "register_operand")]
> + "TARGET_SSE4_1 && !flag_trapping_math"
> +{
> + rtx tmp = gen_reg_rtx (<MODE>mode);
> + emit_insn (gen_round<mode>2 (tmp, operands[1]));
> + emit_insn (gen_fix_trunc<mode><sseintvecmodelower>2 (operands[0], tmp));
> + DONE;
> +})
> +
> (define_expand "round<mode>2_sfix"
> [(match_operand:<sseintvecmode> 0 "register_operand")
> (match_operand:VF1 1 "register_operand")]
> @@ -23868,6 +23941,13 @@ (define_insn
> "*avx512pf_scatterpf<VI4_256_8_512:mode>df_mask"
> (set_attr "prefix" "evex")
> (set_attr "mode" "XI")])
>
> +(define_expand "exp2<mode>2"
> + [(set (match_operand:VF_512 0 "register_operand")
> + (unspec:VF_512
> + [(match_operand:VF_512 1 "vector_operand")]
> + UNSPEC_EXP2))]
> + "TARGET_AVX512ER")
> +
> (define_insn "avx512er_exp2<mode><mask_name><round_saeonly_name>"
> [(set (match_operand:VF_512 0 "register_operand" "=v")
> (unspec:VF_512
> --
> 2.27.0
>
