From 228646a64fc1013f9133159d2e7b05fdd9972772 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Tue, 5 May 2020 09:01:37 +0200 Subject: [PATCH] i386: Simplify {,v}ph{add,sub{,s}{w,d} insn patterns [PR94460] As mentioned in the previous PR94460 patch, the RTL patterns look too large/complicated, we can simplify them by just performing two 2 arg permutations to move the arguments into the right spots and then just doing the plus/minus (or signed saturation version thereof). 2020-05-05 Jakub Jelinek PR target/94460 * config/i386/sse.md (avx2_phwv16hi3, ssse3_phwv8hi3, ssse3_phwv4hi3, avx2_phdv8si3, ssse3_phdv4si3, ssse3_phdv2si3): Simplify RTL patterns. --- gcc/ChangeLog | 8 ++ gcc/config/i386/sse.md | 258 ++++++++++++----------------------------- 2 files changed, 81 insertions(+), 185 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index b534c55760a..34b56d9454f 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,11 @@ +2020-05-05 Jakub Jelinek + + PR target/94460 + * config/i386/sse.md (avx2_phwv16hi3, + ssse3_phwv8hi3, ssse3_phwv4hi3, + avx2_phdv8si3, ssse3_phdv4si3, + ssse3_phdv2si3): Simplify RTL patterns. + 2020-05-04 Clement Chigot David Edelsohn diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 90ced8599ca..0d69c9eb903 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -16038,73 +16038,23 @@ (define_insn "avx2_phwv16hi3" [(set (match_operand:V16HI 0 "register_operand" "=x") - (vec_concat:V16HI - (vec_concat:V8HI - (vec_concat:V4HI - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI - (match_operand:V16HI 1 "register_operand" "x") - (parallel [(const_int 0)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 1)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 2)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 3)])))) - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 4)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 5)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 6)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 7)]))))) - (vec_concat:V4HI - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI - (match_operand:V16HI 2 "nonimmediate_operand" "xm") - (parallel [(const_int 0)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 1)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 2)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 3)])))) - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 4)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 5)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 6)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 7)])))))) - (vec_concat:V8HI - (vec_concat:V4HI - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 8)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 9)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 10)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 11)])))) - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 12)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 13)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 14)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 15)]))))) - (vec_concat:V4HI - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 8)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 9)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 10)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 11)])))) - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 12)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 13)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 14)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 15)]))))))))] + (ssse3_plusminus:V16HI + (vec_select:V16HI + (vec_concat:V32HI + (match_operand:V16HI 1 "register_operand" "x") + (match_operand:V16HI 2 "nonimmediate_operand" "xm")) + (parallel + [(const_int 0) (const_int 2) (const_int 4) (const_int 6) + (const_int 16) (const_int 18) (const_int 20) (const_int 22) + (const_int 8) (const_int 10) (const_int 12) (const_int 14) + (const_int 24) (const_int 26) (const_int 28) (const_int 30)])) + (vec_select:V16HI + (vec_concat:V32HI (match_dup 1) (match_dup 2)) + (parallel + [(const_int 1) (const_int 3) (const_int 5) (const_int 7) + (const_int 17) (const_int 19) (const_int 21) (const_int 23) + (const_int 9) (const_int 11) (const_int 13) (const_int 15) + (const_int 25) (const_int 27) (const_int 29) (const_int 31)]))))] "TARGET_AVX2" "vphw\t{%2, %1, %0|%0, %1, %2}" [(set_attr "type" "sseiadd") @@ -16114,41 +16064,19 @@ (define_insn "ssse3_phwv8hi3" [(set (match_operand:V8HI 0 "register_operand" "=x,x") - (vec_concat:V8HI - (vec_concat:V4HI - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI - (match_operand:V8HI 1 "register_operand" "0,x") - (parallel [(const_int 0)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 1)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 2)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 3)])))) - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 4)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 5)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 6)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 7)]))))) - (vec_concat:V4HI - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI - (match_operand:V8HI 2 "vector_operand" "xBm,xm") - (parallel [(const_int 0)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 1)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 2)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 3)])))) - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 4)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 5)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 6)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 7)])))))))] + (ssse3_plusminus:V8HI + (vec_select:V8HI + (vec_concat:V16HI + (match_operand:V8HI 1 "register_operand" "0,x") + (match_operand:V8HI 2 "vector_operand" "xBm,xm")) + (parallel + [(const_int 0) (const_int 2) (const_int 4) (const_int 6) + (const_int 8) (const_int 10) (const_int 12) (const_int 14)])) + (vec_select:V8HI + (vec_concat:V16HI (match_dup 1) (match_dup 2)) + (parallel + [(const_int 1) (const_int 3) (const_int 5) (const_int 7) + (const_int 9) (const_int 11) (const_int 13) (const_int 15)]))))] "TARGET_SSSE3" "@ phw\t{%2, %0|%0, %2} @@ -16163,25 +16091,17 @@ (define_insn_and_split "ssse3_phwv4hi3" [(set (match_operand:V4HI 0 "register_operand" "=y,x,Yv") - (vec_concat:V4HI - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI - (match_operand:V4HI 1 "register_operand" "0,0,Yv") - (parallel [(const_int 0)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 1)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 1) (parallel [(const_int 2)])) - (vec_select:HI (match_dup 1) (parallel [(const_int 3)])))) - (vec_concat:V2HI - (ssse3_plusminus:HI - (vec_select:HI - (match_operand:V4HI 2 "register_mmxmem_operand" "ym,x,Yv") - (parallel [(const_int 0)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 1)]))) - (ssse3_plusminus:HI - (vec_select:HI (match_dup 2) (parallel [(const_int 2)])) - (vec_select:HI (match_dup 2) (parallel [(const_int 3)]))))))] + (ssse3_plusminus:V4HI + (vec_select:V4HI + (vec_concat:V8HI + (match_operand:V4HI 1 "register_operand" "0,0,Yv") + (match_operand:V4HI 2 "register_mmxmem_operand" "ym,x,Yv")) + (parallel + [(const_int 0) (const_int 2) (const_int 4) (const_int 6)])) + (vec_select:V4HI + (vec_concat:V8HI (match_dup 1) (match_dup 2)) + (parallel + [(const_int 1) (const_int 3) (const_int 5) (const_int 7)]))))] "(TARGET_MMX || TARGET_MMX_WITH_SSE) && TARGET_SSSE3" "@ phw\t{%2, %0|%0, %2} @@ -16211,41 +16131,19 @@ (define_insn "avx2_phdv8si3" [(set (match_operand:V8SI 0 "register_operand" "=x") - (vec_concat:V8SI - (vec_concat:V4SI - (vec_concat:V2SI - (plusminus:SI - (vec_select:SI - (match_operand:V8SI 1 "register_operand" "x") - (parallel [(const_int 0)])) - (vec_select:SI (match_dup 1) (parallel [(const_int 1)]))) - (plusminus:SI - (vec_select:SI (match_dup 1) (parallel [(const_int 2)])) - (vec_select:SI (match_dup 1) (parallel [(const_int 3)])))) - (vec_concat:V2SI - (plusminus:SI - (vec_select:SI - (match_operand:V8SI 2 "nonimmediate_operand" "xm") - (parallel [(const_int 0)])) - (vec_select:SI (match_dup 2) (parallel [(const_int 1)]))) - (plusminus:SI - (vec_select:SI (match_dup 2) (parallel [(const_int 2)])) - (vec_select:SI (match_dup 2) (parallel [(const_int 3)]))))) - (vec_concat:V4SI - (vec_concat:V2SI - (plusminus:SI - (vec_select:SI (match_dup 1) (parallel [(const_int 4)])) - (vec_select:SI (match_dup 1) (parallel [(const_int 5)]))) - (plusminus:SI - (vec_select:SI (match_dup 1) (parallel [(const_int 6)])) - (vec_select:SI (match_dup 1) (parallel [(const_int 7)])))) - (vec_concat:V2SI - (plusminus:SI - (vec_select:SI (match_dup 2) (parallel [(const_int 4)])) - (vec_select:SI (match_dup 2) (parallel [(const_int 5)]))) - (plusminus:SI - (vec_select:SI (match_dup 2) (parallel [(const_int 6)])) - (vec_select:SI (match_dup 2) (parallel [(const_int 7)])))))))] + (plusminus:V8SI + (vec_select:V8SI + (vec_concat:V16SI + (match_operand:V8SI 1 "register_operand" "x") + (match_operand:V8SI 2 "nonimmediate_operand" "xm")) + (parallel + [(const_int 0) (const_int 2) (const_int 8) (const_int 10) + (const_int 4) (const_int 6) (const_int 12) (const_int 14)])) + (vec_select:V8SI + (vec_concat:V16SI (match_dup 1) (match_dup 2)) + (parallel + [(const_int 1) (const_int 3) (const_int 9) (const_int 11) + (const_int 5) (const_int 7) (const_int 13) (const_int 15)]))))] "TARGET_AVX2" "vphd\t{%2, %1, %0|%0, %1, %2}" [(set_attr "type" "sseiadd") @@ -16255,25 +16153,17 @@ (define_insn "ssse3_phdv4si3" [(set (match_operand:V4SI 0 "register_operand" "=x,x") - (vec_concat:V4SI - (vec_concat:V2SI - (plusminus:SI - (vec_select:SI - (match_operand:V4SI 1 "register_operand" "0,x") - (parallel [(const_int 0)])) - (vec_select:SI (match_dup 1) (parallel [(const_int 1)]))) - (plusminus:SI - (vec_select:SI (match_dup 1) (parallel [(const_int 2)])) - (vec_select:SI (match_dup 1) (parallel [(const_int 3)])))) - (vec_concat:V2SI - (plusminus:SI - (vec_select:SI - (match_operand:V4SI 2 "vector_operand" "xBm,xm") - (parallel [(const_int 0)])) - (vec_select:SI (match_dup 2) (parallel [(const_int 1)]))) - (plusminus:SI - (vec_select:SI (match_dup 2) (parallel [(const_int 2)])) - (vec_select:SI (match_dup 2) (parallel [(const_int 3)]))))))] + (plusminus:V4SI + (vec_select:V4SI + (vec_concat:V8SI + (match_operand:V4SI 1 "register_operand" "0,x") + (match_operand:V4SI 2 "vector_operand" "xBm,xm")) + (parallel + [(const_int 0) (const_int 2) (const_int 4) (const_int 6)])) + (vec_select:V4SI + (vec_concat:V8SI (match_dup 1) (match_dup 2)) + (parallel + [(const_int 1) (const_int 3) (const_int 5) (const_int 7)]))))] "TARGET_SSSE3" "@ phd\t{%2, %0|%0, %2} @@ -16288,17 +16178,15 @@ (define_insn_and_split "ssse3_phdv2si3" [(set (match_operand:V2SI 0 "register_operand" "=y,x,Yv") - (vec_concat:V2SI - (plusminus:SI - (vec_select:SI + (plusminus:V2SI + (vec_select:V2SI + (vec_concat:V4SI (match_operand:V2SI 1 "register_operand" "0,0,Yv") - (parallel [(const_int 0)])) - (vec_select:SI (match_dup 1) (parallel [(const_int 1)]))) - (plusminus:SI - (vec_select:SI - (match_operand:V2SI 2 "register_mmxmem_operand" "ym,x,Yv") - (parallel [(const_int 0)])) - (vec_select:SI (match_dup 2) (parallel [(const_int 1)])))))] + (match_operand:V2SI 2 "register_mmxmem_operand" "ym,x,Yv")) + (parallel [(const_int 0) (const_int 2)])) + (vec_select:V2SI + (vec_concat:V4SI (match_dup 1) (match_dup 2)) + (parallel [(const_int 1) (const_int 3)]))))] "(TARGET_MMX || TARGET_MMX_WITH_SSE) && TARGET_SSSE3" "@ phd\t{%2, %0|%0, %2} -- 2.30.2