[llvm] faea1c5 - [X86] Add test case showing failure to fold concat_v32i8(trunc_v16i16(x),trunc_v16i16(y)) -> trunc_v32i16(concat_v16i16(x,y))

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2023-03-09T12:10:51Z
New Revision: faea1c5ccc936d0159d55727df7617398c20130a

URL: https://github.com/llvm/llvm-project/commit/faea1c5ccc936d0159d55727df7617398c20130a
DIFF: https://github.com/llvm/llvm-project/commit/faea1c5ccc936d0159d55727df7617398c20130a.diff

LOG: [X86] Add test case showing failure to fold concat_v32i8(trunc_v16i16(x),trunc_v16i16(y)) -> trunc_v32i16(concat_v16i16(x,y))

We have similar tests but nothing that should only fold on BWI targets

Added: 
    

Modified: 
    llvm/test/CodeGen/X86/vector-trunc.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/X86/vector-trunc.ll b/llvm/test/CodeGen/X86/vector-trunc.ll
index c7bf6daf803a..b3147c1d87a8 100644
--- a/llvm/test/CodeGen/X86/vector-trunc.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc.ll
@@ -1743,6 +1743,80 @@ entry:
   ret i64 %1
 }
 
+define <32 x i8> @trunc2x16i16_32i8(<16 x i16> %a, <16 x i16> %b) {
+; SSE-LABEL: trunc2x16i16_32i8:
+; SSE:       # %bb.0: # %entry
+; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; SSE-NEXT:    pand %xmm4, %xmm1
+; SSE-NEXT:    pand %xmm4, %xmm0
+; SSE-NEXT:    packuswb %xmm1, %xmm0
+; SSE-NEXT:    pand %xmm4, %xmm3
+; SSE-NEXT:    pand %xmm2, %xmm4
+; SSE-NEXT:    packuswb %xmm3, %xmm4
+; SSE-NEXT:    movdqa %xmm4, %xmm1
+; SSE-NEXT:    retq
+;
+; AVX1-LABEL: trunc2x16i16_32i8:
+; AVX1:       # %bb.0: # %entry
+; AVX1-NEXT:    vmovaps {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX1-NEXT:    vandps %ymm2, %ymm0, %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vpackuswb %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vandps %ymm2, %ymm1, %ymm1
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc2x16i16_32i8:
+; AVX2:       # %bb.0: # %entry
+; AVX2-NEXT:    vpbroadcastw {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX2-NEXT:    vpackuswb %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; AVX2-NEXT:    retq
+;
+; AVX512F-LABEL: trunc2x16i16_32i8:
+; AVX512F:       # %bb.0: # %entry
+; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
+; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
+; AVX512F-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc2x16i16_32i8:
+; AVX512VL:       # %bb.0: # %entry
+; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
+; AVX512VL-NEXT:    vpmovdb %zmm1, %xmm1
+; AVX512VL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc2x16i16_32i8:
+; AVX512BW:       # %bb.0: # %entry
+; AVX512BW-NEXT:    # kill: def $ymm1 killed $ymm1 def $zmm1
+; AVX512BW-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512BW-NEXT:    vpmovwb %zmm0, %ymm0
+; AVX512BW-NEXT:    vpmovwb %zmm1, %ymm1
+; AVX512BW-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc2x16i16_32i8:
+; AVX512BWVL:       # %bb.0: # %entry
+; AVX512BWVL-NEXT:    vpmovwb %ymm0, %xmm0
+; AVX512BWVL-NEXT:    vpmovwb %ymm1, %xmm1
+; AVX512BWVL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX512BWVL-NEXT:    retq
+entry:
+  %0 = trunc <16 x i16> %a to <16 x i8>
+  %1 = trunc <16 x i16> %b to <16 x i8>
+  %2 = shufflevector <16 x i8> %0, <16 x i8> %1, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+  ret <32 x i8> %2
+}
+
 define <16 x i8> @trunc2x8i16_16i8(<8 x i16> %a, <8 x i16> %b) {
 ; SSE2-LABEL: trunc2x8i16_16i8:
 ; SSE2:       # %bb.0: # %entry