-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -x86-experimental-vector-shuffle-legality | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse3 -x86-experimental-vector-shuffle-legality | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE3
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 -x86-experimental-vector-shuffle-legality | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 -x86-experimental-vector-shuffle-legality | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx -x86-experimental-vector-shuffle-legality | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 -x86-experimental-vector-shuffle-legality | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE3
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define <4 x i32> @shuffle_v4i32_0451(<4 x i32> %a, <4 x i32> %b) {
; SSE2-LABEL: shuffle_v4i32_0451:
; SSE2: # BB#0:
-; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1]
-; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,3,1]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
; SSE2-NEXT: retq
;
; SSE3-LABEL: shuffle_v4i32_0451:
; SSE3: # BB#0:
-; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1]
-; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,3,1]
+; SSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: shuffle_v4i32_0451:
; SSSE3: # BB#0:
-; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1]
-; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,3,1]
+; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: shuffle_v4i32_0451:
define <4 x i32> @shuffle_v4i32_4015(<4 x i32> %a, <4 x i32> %b) {
; SSE2-LABEL: shuffle_v4i32_4015:
; SSE2: # BB#0:
-; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1]
-; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0,1,3]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,0,2,3]
; SSE2-NEXT: retq
;
; SSE3-LABEL: shuffle_v4i32_4015:
; SSE3: # BB#0:
-; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1]
-; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0,1,3]
+; SSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,0,2,3]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: shuffle_v4i32_4015:
; SSSE3: # BB#0:
-; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1]
-; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0,1,3]
+; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,0,2,3]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: shuffle_v4i32_4015:
define <4 x float> @shuffle_v4f32_u051(<4 x float> %a, <4 x float> %b) {
; SSE-LABEL: shuffle_v4f32_u051:
; SSE: # BB#0:
-; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,0],xmm0[1,0]
-; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,2]
+; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: shuffle_v4f32_u051:
; AVX: # BB#0:
-; AVX-NEXT: vshufps {{.*#+}} xmm1 = xmm1[1,0],xmm0[1,0]
-; AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,2]
+; AVX-NEXT: vunpcklps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; AVX-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 undef, i32 0, i32 5, i32 1>
ret <4 x float> %shuffle
}
define <4 x i32> @shuffle_v4i32_40u1(<4 x i32> %a, <4 x i32> %b) {
-; SSE2-LABEL: shuffle_v4i32_40u1:
-; SSE2: # BB#0:
-; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[0,0]
-; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2],xmm0[2,1]
-; SSE2-NEXT: movaps %xmm1, %xmm0
-; SSE2-NEXT: retq
-;
-; SSE3-LABEL: shuffle_v4i32_40u1:
-; SSE3: # BB#0:
-; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[0,0]
-; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2],xmm0[2,1]
-; SSE3-NEXT: movaps %xmm1, %xmm0
-; SSE3-NEXT: retq
-;
-; SSSE3-LABEL: shuffle_v4i32_40u1:
-; SSSE3: # BB#0:
-; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[0,0]
-; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2],xmm0[2,1]
-; SSSE3-NEXT: movaps %xmm1, %xmm0
-; SSSE3-NEXT: retq
-;
-; SSE41-LABEL: shuffle_v4i32_40u1:
-; SSE41: # BB#0:
-; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
-; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3,4,5,6,7]
-; SSE41-NEXT: retq
-;
-; AVX1-LABEL: shuffle_v4i32_40u1:
-; AVX1: # BB#0:
-; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
-; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3,4,5,6,7]
-; AVX1-NEXT: retq
+; SSE-LABEL: shuffle_v4i32_40u1:
+; SSE: # BB#0:
+; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE-NEXT: movdqa %xmm1, %xmm0
+; SSE-NEXT: retq
;
-; AVX2-LABEL: shuffle_v4i32_40u1:
-; AVX2: # BB#0:
-; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
-; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
-; AVX2-NEXT: retq
+; AVX-LABEL: shuffle_v4i32_40u1:
+; AVX: # BB#0:
+; AVX-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; AVX-NEXT: retq
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 4, i32 0, i32 undef, i32 1>
ret <4 x i32> %shuffle
}
ret <4 x i32> %shuffle
}
+define <4 x i32> @shuffle_v4i32_bitcast_0415(<4 x i32> %a, <4 x i32> %b) {
+; SSE-LABEL: shuffle_v4i32_bitcast_0415:
+; SSE: # BB#0:
+; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE-NEXT: retq
+;
+; AVX-LABEL: shuffle_v4i32_bitcast_0415:
+; AVX: # BB#0:
+; AVX-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX-NEXT: retq
+ %shuffle32 = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 1, i32 5, i32 0, i32 4>
+ %bitcast64 = bitcast <4 x i32> %shuffle32 to <2 x double>
+ %shuffle64 = shufflevector <2 x double> %bitcast64, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+ %bitcast32 = bitcast <2 x double> %shuffle64 to <4 x i32>
+ ret <4 x i32> %bitcast32
+}
+
define <4 x i32> @insert_reg_and_zero_v4i32(i32 %a) {
; SSE-LABEL: insert_reg_and_zero_v4i32:
; SSE: # BB#0:
; AVX: # BB#0:
; AVX-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT: retq
- %a = load i32* %ptr
+ %a = load i32, i32* %ptr
%v = insertelement <4 x i32> undef, i32 %a, i32 0
%shuffle = shufflevector <4 x i32> %v, <4 x i32> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x i32> %shuffle
; AVX: # BB#0:
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT: retq
- %a = load float* %ptr
+ %a = load float, float* %ptr
%v = insertelement <4 x float> undef, float %a, i32 0
%shuffle = shufflevector <4 x float> %v, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x float> %shuffle
; AVX2-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX2-NEXT: retq
- %a = load <2 x i32>* %ptr
+ %a = load <2 x i32>, <2 x i32>* %ptr
%v = shufflevector <2 x i32> %a, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%shuffle = shufflevector <4 x i32> %v, <4 x i32> %b, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
ret <4 x i32> %shuffle
; AVX-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-NEXT: retq
- %a = load <2 x i32>* %ptr
+ %a = load <2 x i32>, <2 x i32>* %ptr
%v = shufflevector <2 x i32> %a, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%shuffle = shufflevector <4 x i32> %v, <4 x i32> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x i32> %shuffle
; AVX: # BB#0:
; AVX-NEXT: vmovlpd (%rdi), %xmm0, %xmm0
; AVX-NEXT: retq
- %a = load <2 x float>* %ptr
+ %a = load <2 x float>, <2 x float>* %ptr
%v = shufflevector <2 x float> %a, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%shuffle = shufflevector <4 x float> %v, <4 x float> %b, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
ret <4 x float> %shuffle
; AVX: # BB#0:
; AVX-NEXT: vmovhpd (%rdi), %xmm0, %xmm0
; AVX-NEXT: retq
- %a = load <2 x float>* %ptr
+ %a = load <2 x float>, <2 x float>* %ptr
%v = shufflevector <2 x float> %a, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%shuffle = shufflevector <4 x float> %v, <4 x float> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x float> %shuffle
; AVX: # BB#0:
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = mem[3,2,1,0]
; AVX-NEXT: retq
- %a = load <4 x float>* %ptr
+ %a = load <4 x float>, <4 x float>* %ptr
%shuffle = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %shuffle
}