summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/vector-rotate-128.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/X86/vector-rotate-128.ll')
-rw-r--r--test/CodeGen/X86/vector-rotate-128.ll76
1 files changed, 52 insertions, 24 deletions
diff --git a/test/CodeGen/X86/vector-rotate-128.ll b/test/CodeGen/X86/vector-rotate-128.ll
index b40c9eddd46b..8af96c168be6 100644
--- a/test/CodeGen/X86/vector-rotate-128.ll
+++ b/test/CodeGen/X86/vector-rotate-128.ll
@@ -699,20 +699,35 @@ define <16 x i8> @var_rotate_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
; AVX-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
-; AVX512-LABEL: var_rotate_v16i8:
-; AVX512: # %bb.0:
-; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
-; AVX512-NEXT: vpsubb %xmm1, %xmm2, %xmm2
-; AVX512-NEXT: vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
-; AVX512-NEXT: vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
-; AVX512-NEXT: vpsllvd %zmm1, %zmm0, %zmm1
-; AVX512-NEXT: vpmovdb %zmm1, %xmm1
-; AVX512-NEXT: vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
-; AVX512-NEXT: vpsrlvd %zmm2, %zmm0, %zmm0
-; AVX512-NEXT: vpmovdb %zmm0, %xmm0
-; AVX512-NEXT: vpor %xmm0, %xmm1, %xmm0
-; AVX512-NEXT: vzeroupper
-; AVX512-NEXT: retq
+; AVX512BW-LABEL: var_rotate_v16i8:
+; AVX512BW: # %bb.0:
+; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
+; AVX512BW-NEXT: vpsubb %xmm1, %xmm2, %xmm2
+; AVX512BW-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
+; AVX512BW-NEXT: vpmovzxbw {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
+; AVX512BW-NEXT: vpsllvw %zmm1, %zmm0, %zmm1
+; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
+; AVX512BW-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero,xmm2[8],zero,xmm2[9],zero,xmm2[10],zero,xmm2[11],zero,xmm2[12],zero,xmm2[13],zero,xmm2[14],zero,xmm2[15],zero
+; AVX512BW-NEXT: vpsrlvw %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
+; AVX512BW-NEXT: vpor %xmm0, %xmm1, %xmm0
+; AVX512BW-NEXT: vzeroupper
+; AVX512BW-NEXT: retq
+;
+; AVX512VL-LABEL: var_rotate_v16i8:
+; AVX512VL: # %bb.0:
+; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
+; AVX512VL-NEXT: vpsubb %xmm1, %xmm2, %xmm2
+; AVX512VL-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
+; AVX512VL-NEXT: vpmovzxbw {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
+; AVX512VL-NEXT: vpsllvw %ymm1, %ymm0, %ymm1
+; AVX512VL-NEXT: vpmovwb %ymm1, %xmm1
+; AVX512VL-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero,xmm2[8],zero,xmm2[9],zero,xmm2[10],zero,xmm2[11],zero,xmm2[12],zero,xmm2[13],zero,xmm2[14],zero,xmm2[15],zero
+; AVX512VL-NEXT: vpsrlvw %ymm2, %ymm0, %ymm0
+; AVX512VL-NEXT: vpmovwb %ymm0, %xmm0
+; AVX512VL-NEXT: vpor %xmm0, %xmm1, %xmm0
+; AVX512VL-NEXT: vzeroupper
+; AVX512VL-NEXT: retq
;
; XOP-LABEL: var_rotate_v16i8:
; XOP: # %bb.0:
@@ -1249,16 +1264,29 @@ define <16 x i8> @constant_rotate_v16i8(<16 x i8> %a) nounwind {
; AVX-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
-; AVX512-LABEL: constant_rotate_v16i8:
-; AVX512: # %bb.0:
-; AVX512-NEXT: vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
-; AVX512-NEXT: vpsllvd {{.*}}(%rip), %zmm0, %zmm1
-; AVX512-NEXT: vpmovdb %zmm1, %xmm1
-; AVX512-NEXT: vpsrlvd {{.*}}(%rip), %zmm0, %zmm0
-; AVX512-NEXT: vpmovdb %zmm0, %xmm0
-; AVX512-NEXT: vpor %xmm0, %xmm1, %xmm0
-; AVX512-NEXT: vzeroupper
-; AVX512-NEXT: retq
+; AVX512BW-LABEL: constant_rotate_v16i8:
+; AVX512BW: # %bb.0:
+; AVX512BW-NEXT: vmovdqa {{.*#+}} ymm1 = [0,1,2,3,4,5,6,7,8,7,6,5,4,3,2,1]
+; AVX512BW-NEXT: vpmovzxbw {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
+; AVX512BW-NEXT: vpsllvw %zmm1, %zmm0, %zmm1
+; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
+; AVX512BW-NEXT: vmovdqa {{.*#+}} ymm2 = [8,7,6,5,4,3,2,1,0,1,2,3,4,5,6,7]
+; AVX512BW-NEXT: vpsrlvw %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
+; AVX512BW-NEXT: vpor %xmm0, %xmm1, %xmm0
+; AVX512BW-NEXT: vzeroupper
+; AVX512BW-NEXT: retq
+;
+; AVX512VL-LABEL: constant_rotate_v16i8:
+; AVX512VL: # %bb.0:
+; AVX512VL-NEXT: vpmovzxbw {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
+; AVX512VL-NEXT: vpsllvw {{.*}}(%rip), %ymm0, %ymm1
+; AVX512VL-NEXT: vpmovwb %ymm1, %xmm1
+; AVX512VL-NEXT: vpsrlvw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VL-NEXT: vpmovwb %ymm0, %xmm0
+; AVX512VL-NEXT: vpor %xmm0, %xmm1, %xmm0
+; AVX512VL-NEXT: vzeroupper
+; AVX512VL-NEXT: retq
;
; XOP-LABEL: constant_rotate_v16i8:
; XOP: # %bb.0:
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-10 14:45:33 +0000