On 2/16/19, H.J. Lu <hjl.to...@gmail.com> wrote:
> There is no V4HI pmulhrsw in AVX512BW and V4HI/V8HI pmulhrsw don't require
> AVX2. To support TARGET_MMX_WITH_SSE, replace nonimmediate_operand with
> register_pmulhrswmem_operand in <ssse3_avx2>_pmulhrsw<mode>3.
>
> PR target/89372
> * config/i386/predicates.md (register_pmulhrswmem_operand): New.
> * config/i386/sse.md (PMULHRSW): Remove V4HI.
> (PMULHRSW_MMX): New.
> (<ssse3_avx2>_pmulhrsw<mode>3): Replace PMULHRSW with
> PMULHRSW_MMX. Require TARGET_SSSE3, not TARGET_AVX2. Replace
> nonimmediate_operand with register_pmulhrswmem_operand.
Complications like the above usually points to wrong macroization
choice. Please try to split out V4HImode pattern.
Also, please separate the fix to a separate patch, which should be
committed independently as a fix before gcc-9 is released.
Uros.
> ---
> gcc/config/i386/predicates.md | 7 +++++++
> gcc/config/i386/sse.md | 15 +++++++++------
> 2 files changed, 16 insertions(+), 6 deletions(-)
>
> diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
> index f3c2f72de54..b7cb26a81fe 100644
> --- a/gcc/config/i386/predicates.md
> +++ b/gcc/config/i386/predicates.md
> @@ -56,6 +56,13 @@
> (and (not (match_test "TARGET_MMX_WITH_SSE"))
> (match_operand 0 "memory_operand"))))
>
> +;; Match register operands, but include memory operands for
> +;; !(TARGET_MMX_WITH_SSE && mode == V4HImode).
> +(define_predicate "register_pmulhrswmem_operand"
> + (ior (match_operand 0 "register_operand")
> + (and (not (match_test "TARGET_MMX_WITH_SSE && mode == V4HImode"))
> + (match_operand 0 "memory_operand"))))
> +
> ;; True if the operand is an SSE register.
> (define_predicate "sse_reg_operand"
> (and (match_code "reg")
> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> index 92f5ad17156..379da16615d 100644
> --- a/gcc/config/i386/sse.md
> +++ b/gcc/config/i386/sse.md
> @@ -15579,7 +15579,7 @@
> (set_attr "mode" "DI,TI,TI")])
>
> (define_mode_iterator PMULHRSW
> - [V4HI V8HI (V16HI "TARGET_AVX2")])
> + [V8HI (V16HI "TARGET_AVX2")])
>
> (define_expand "<ssse3_avx2>_pmulhrsw<mode>3_mask"
> [(set (match_operand:PMULHRSW 0 "register_operand")
> @@ -15604,21 +15604,24 @@
> ix86_fixup_binary_operands_no_copy (MULT, <MODE>mode, operands);
> })
>
> +(define_mode_iterator PMULHRSW_MMX
> + [V4HI V8HI (V16HI "TARGET_AVX2")])
> +
> (define_expand "<ssse3_avx2>_pmulhrsw<mode>3"
> - [(set (match_operand:PMULHRSW 0 "register_operand")
> - (truncate:PMULHRSW
> + [(set (match_operand:PMULHRSW_MMX 0 "register_operand")
> + (truncate:PMULHRSW_MMX
> (lshiftrt:<ssedoublemode>
> (plus:<ssedoublemode>
> (lshiftrt:<ssedoublemode>
> (mult:<ssedoublemode>
> (sign_extend:<ssedoublemode>
> - (match_operand:PMULHRSW 1 "nonimmediate_operand"))
> + (match_operand:PMULHRSW_MMX 1
> "register_pmulhrswmem_operand"))
> (sign_extend:<ssedoublemode>
> - (match_operand:PMULHRSW 2 "nonimmediate_operand")))
> + (match_operand:PMULHRSW_MMX 2
> "register_pmulhrswmem_operand")))
> (const_int 14))
> (match_dup 3))
> (const_int 1))))]
> - "TARGET_AVX2"
> + "TARGET_SSSE3"
> {
> operands[3] = CONST1_RTX(<MODE>mode);
> ix86_fixup_binary_operands_no_copy (MULT, <MODE>mode, operands);
> --
> 2.20.1
>
>
