summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/shuffle-strided-with-offset-256.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/X86/shuffle-strided-with-offset-256.ll')
-rw-r--r--test/CodeGen/X86/shuffle-strided-with-offset-256.ll149
1 files changed, 84 insertions, 65 deletions
diff --git a/test/CodeGen/X86/shuffle-strided-with-offset-256.ll b/test/CodeGen/X86/shuffle-strided-with-offset-256.ll
index 7cef269ebc2b8..081c962ab94a9 100644
--- a/test/CodeGen/X86/shuffle-strided-with-offset-256.ll
+++ b/test/CodeGen/X86/shuffle-strided-with-offset-256.ll
@@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX2-SLOW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-shuffle | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX2-FAST
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BW
@@ -362,18 +363,30 @@ define void @shuffle_v16i16_to_v4i16_1(<16 x i16>* %L, <4 x i16>* %S) nounwind {
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
-; AVX2-LABEL: shuffle_v16i16_to_v4i16_1:
-; AVX2: # %bb.0:
-; AVX2-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; AVX2-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,3,2,3,4,5,6,7]
-; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; AVX2-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
-; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; AVX2-NEXT: vmovq %xmm0, (%rsi)
-; AVX2-NEXT: vzeroupper
-; AVX2-NEXT: retq
+; AVX2-SLOW-LABEL: shuffle_v16i16_to_v4i16_1:
+; AVX2-SLOW: # %bb.0:
+; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
+; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,3,2,3,4,5,6,7]
+; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
+; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-SLOW-NEXT: vmovq %xmm0, (%rsi)
+; AVX2-SLOW-NEXT: vzeroupper
+; AVX2-SLOW-NEXT: retq
+;
+; AVX2-FAST-LABEL: shuffle_v16i16_to_v4i16_1:
+; AVX2-FAST: # %bb.0:
+; AVX2-FAST-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = [2,3,10,11,8,9,10,11,8,9,10,11,12,13,14,15]
+; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-FAST-NEXT: vmovq %xmm0, (%rsi)
+; AVX2-FAST-NEXT: vzeroupper
+; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX512F: # %bb.0:
@@ -446,18 +459,30 @@ define void @shuffle_v16i16_to_v4i16_2(<16 x i16>* %L, <4 x i16>* %S) nounwind {
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
-; AVX2-LABEL: shuffle_v16i16_to_v4i16_2:
-; AVX2: # %bb.0:
-; AVX2-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
-; AVX2-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[2,0,2,3,4,5,6,7]
-; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
-; AVX2-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
-; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; AVX2-NEXT: vmovq %xmm0, (%rsi)
-; AVX2-NEXT: vzeroupper
-; AVX2-NEXT: retq
+; AVX2-SLOW-LABEL: shuffle_v16i16_to_v4i16_2:
+; AVX2-SLOW: # %bb.0:
+; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
+; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[2,0,2,3,4,5,6,7]
+; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
+; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
+; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-SLOW-NEXT: vmovq %xmm0, (%rsi)
+; AVX2-SLOW-NEXT: vzeroupper
+; AVX2-SLOW-NEXT: retq
+;
+; AVX2-FAST-LABEL: shuffle_v16i16_to_v4i16_2:
+; AVX2-FAST: # %bb.0:
+; AVX2-FAST-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = [4,5,12,13,4,5,6,7,8,9,10,11,12,13,14,15]
+; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-FAST-NEXT: vmovq %xmm0, (%rsi)
+; AVX2-FAST-NEXT: vzeroupper
+; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX512F: # %bb.0:
@@ -522,18 +547,30 @@ define void @shuffle_v16i16_to_v4i16_3(<16 x i16>* %L, <4 x i16>* %S) nounwind {
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
-; AVX2-LABEL: shuffle_v16i16_to_v4i16_3:
-; AVX2: # %bb.0:
-; AVX2-NEXT: vmovdqa (%rdi), %ymm0
-; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
-; AVX2-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
-; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
-; AVX2-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
-; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; AVX2-NEXT: vmovq %xmm0, (%rsi)
-; AVX2-NEXT: vzeroupper
-; AVX2-NEXT: retq
+; AVX2-SLOW-LABEL: shuffle_v16i16_to_v4i16_3:
+; AVX2-SLOW: # %bb.0:
+; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
+; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
+; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
+; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
+; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-SLOW-NEXT: vmovq %xmm0, (%rsi)
+; AVX2-SLOW-NEXT: vzeroupper
+; AVX2-SLOW-NEXT: retq
+;
+; AVX2-FAST-LABEL: shuffle_v16i16_to_v4i16_3:
+; AVX2-FAST: # %bb.0:
+; AVX2-FAST-NEXT: vmovdqa (%rdi), %ymm0
+; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = [6,7,14,15,4,5,6,7,8,9,10,11,12,13,14,15]
+; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-FAST-NEXT: vmovq %xmm0, (%rsi)
+; AVX2-FAST-NEXT: vzeroupper
+; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX512F: # %bb.0:
@@ -633,11 +670,9 @@ define void @shuffle_v32i8_to_v4i8_1(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,1,1,8,8,9,9,8,8,9,9,10,10,11,11]
+; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [1,1,255,255,9,9,255,255,9,9,255,255,11,11,255,255]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
-; AVX512VL-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
-; AVX512VL-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
@@ -659,11 +694,9 @@ define void @shuffle_v32i8_to_v4i8_1(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,1,1,8,8,9,9,8,8,9,9,10,10,11,11]
+; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [1,1,255,255,9,9,255,255,9,9,255,255,11,11,255,255]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
-; AVX512BWVL-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
-; AVX512BWVL-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
@@ -795,11 +828,9 @@ define void @shuffle_v32i8_to_v4i8_3(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [10,10,11,11,2,2,3,3,8,8,9,9,10,10,11,11]
+; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [3,3,11,11,11,11,3,3,8,8,9,9,10,10,11,11]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
-; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
-; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
@@ -821,11 +852,9 @@ define void @shuffle_v32i8_to_v4i8_3(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [10,10,11,11,2,2,3,3,8,8,9,9,10,10,11,11]
+; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [3,3,11,11,11,11,3,3,8,8,9,9,10,10,11,11]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
-; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
-; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
@@ -949,14 +978,9 @@ define void @shuffle_v32i8_to_v4i8_5(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX512VL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
-; AVX512VL-NEXT: vpunpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; AVX512VL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
-; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
-; AVX512VL-NEXT: vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
+; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [5,5,13,13,13,13,5,5,4,4,5,5,6,6,7,7]
+; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
+; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
@@ -978,14 +1002,9 @@ define void @shuffle_v32i8_to_v4i8_5(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
-; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
-; AVX512BWVL-NEXT: vpunpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
-; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
-; AVX512BWVL-NEXT: vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
+; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [5,5,13,13,13,13,5,5,4,4,5,5,6,6,7,7]
+; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
+; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
generated by cgit v1.2.3 (git 2.25.1) at 2025-11-02 07:22:05 +0000