On Sun, Apr 28, 2024 at 7:47 AM liuhongt <hongtao....@intel.com> wrote:
>
> So when both source operand and dest operand require avx512 MASK_REGS, RA
> can allocate MASK_REGS register instead of GPR to avoid reload it from
> GPR to MASK_REGS.
> It's similar as what did for logic patterns.
>
> Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> Ok for trunk?
>
> gcc/ChangeLog:
>
> * config/i386/i386.md: (zero_extendsidi2): Adjust
> alternative *k to ?k.
> (zero_extend<mode>di2): Ditto.
> (*zero_extend<mode>si2): Ditto.
> (*zero_extendqihi2): Ditto.
OK.
Thanks,
Uros.
> ---
> gcc/config/i386/i386.md | 16 +++----
> .../gcc.target/i386/zero_extendkmask.c | 43 +++++++++++++++++++
> 2 files changed, 51 insertions(+), 8 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/zero_extendkmask.c
>
> diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
> index d4ce3809e6d..f2ab7fdcd58 100644
> --- a/gcc/config/i386/i386.md
> +++ b/gcc/config/i386/i386.md
> @@ -4567,10 +4567,10 @@ (define_expand "zero_extendsidi2"
>
> (define_insn "*zero_extendsidi2"
> [(set (match_operand:DI 0 "nonimmediate_operand"
> - "=r,?r,?o,r ,o,?*y,?!*y,$r,$v,$x,*x,*v,*r,*k")
> + "=r,?r,?o,r ,o,?*y,?!*y,$r,$v,$x,*x,*v,?r,?k")
> (zero_extend:DI
> (match_operand:SI 1 "x86_64_zext_operand"
> - "0 ,rm,r ,rmWz,0,r ,m ,v ,r ,m ,*x,*v,*k,*km")))]
> + "0 ,rm,r ,rmWz,0,r ,m ,v ,r ,m ,*x,*v,?k,?km")))]
> ""
> {
> switch (get_attr_type (insn))
> @@ -4703,9 +4703,9 @@ (define_mode_attr kmov_isa
> [(QI "avx512dq") (HI "avx512f") (SI "avx512bw") (DI "avx512bw")])
>
> (define_insn "zero_extend<mode>di2"
> - [(set (match_operand:DI 0 "register_operand" "=r,*r,*k")
> + [(set (match_operand:DI 0 "register_operand" "=r,?r,?k")
> (zero_extend:DI
> - (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,*k,*km")))]
> + (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,?k,?km")))]
> "TARGET_64BIT"
> "@
> movz{<imodesuffix>l|x}\t{%1, %k0|%k0, %1}
> @@ -4758,9 +4758,9 @@ (define_insn_and_split "zero_extend<mode>si2_and"
> (set_attr "mode" "SI")])
>
> (define_insn "*zero_extend<mode>si2"
> - [(set (match_operand:SI 0 "register_operand" "=r,*r,*k")
> + [(set (match_operand:SI 0 "register_operand" "=r,?r,?k")
> (zero_extend:SI
> - (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,*k,*km")))]
> + (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,?k,?km")))]
> "!(TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))"
> "@
> movz{<imodesuffix>l|x}\t{%1, %0|%0, %1}
> @@ -4813,8 +4813,8 @@ (define_insn_and_split "zero_extendqihi2_and"
>
> ; zero extend to SImode to avoid partial register stalls
> (define_insn "*zero_extendqihi2"
> - [(set (match_operand:HI 0 "register_operand" "=r,*r,*k")
> - (zero_extend:HI (match_operand:QI 1 "nonimmediate_operand"
> "qm,*k,*km")))]
> + [(set (match_operand:HI 0 "register_operand" "=r,?r,?k")
> + (zero_extend:HI (match_operand:QI 1 "nonimmediate_operand"
> "qm,?k,?km")))]
> "!(TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))"
> "@
> movz{bl|x}\t{%1, %k0|%k0, %1}
> diff --git a/gcc/testsuite/gcc.target/i386/zero_extendkmask.c
> b/gcc/testsuite/gcc.target/i386/zero_extendkmask.c
> new file mode 100644
> index 00000000000..6b18980bbd1
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/zero_extendkmask.c
> @@ -0,0 +1,43 @@
> +/* { dg-do compile { target { ! ia32 } } } */
> +/* { dg-options "-march=x86-64-v4 -O2" } */
> +/* { dg-final { scan-assembler-not {(?n)shr[bwl]} } } */
> +/* { dg-final { scan-assembler-not {(?n)movz[bw]} } } */
> +
> +#include<immintrin.h>
> +
> +__m512
> +foo (__m512d a, __m512d b, __m512 c, __m512 d)
> +{
> + return _mm512_mask_mov_ps (c, (__mmask16) (_mm512_cmpeq_pd_mask (a, b) >>
> 1), d);
> +}
> +
> +
> +__m512i
> +foo1 (__m512d a, __m512d b, __m512i c, __m512i d)
> +{
> + return _mm512_mask_mov_epi16 (c, (__mmask32) (_mm512_cmpeq_pd_mask (a, b)
> >> 1), d);
> +}
> +
> +__m512i
> +foo2 (__m512d a, __m512d b, __m512i c, __m512i d)
> +{
> + return _mm512_mask_mov_epi8 (c, (__mmask64) (_mm512_cmpeq_pd_mask (a, b)
> >> 1), d);
> +}
> +
> +__m512i
> +foo3 (__m512 a, __m512 b, __m512i c, __m512i d)
> +{
> + return _mm512_mask_mov_epi16 (c, (__mmask32) (_mm512_cmpeq_ps_mask (a, b)
> >> 1), d);
> +}
> +
> +__m512i
> +foo4 (__m512 a, __m512 b, __m512i c, __m512i d)
> +{
> + return _mm512_mask_mov_epi8 (c, (__mmask64) (_mm512_cmpeq_ps_mask (a, b)
> >> 1), d);
> +}
> +
> +__m512i
> +foo5 (__m512i a, __m512i b, __m512i c, __m512i d)
> +{
> + return _mm512_mask_mov_epi8 (c, (__mmask64) (_mm512_cmp_epi16_mask (a, b,
> 5) >> 1), d);
> +}
> --
> 2.31.1
>
