[llvm] r253449 - [X86][AVX] Added 256-bit shuffle splat tests.
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 18 01:39:38 PST 2015
Author: rksimon
Date: Wed Nov 18 03:39:38 2015
New Revision: 253449
URL: http://llvm.org/viewvc/llvm-project?rev=253449&view=rev
Log:
[X86][AVX] Added 256-bit shuffle splat tests.
Modified:
llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v16.ll
llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll
llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v4.ll
llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v8.ll
Modified: llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v16.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v16.ll?rev=253449&r1=253448&r2=253449&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v16.ll (original)
+++ llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v16.ll Wed Nov 18 03:39:38 2015
@@ -3249,6 +3249,56 @@ define <16 x i16> @shuffle_v16i16_23_uu_
ret <16 x i16> %shuffle
}
+define <16 x i16> @shuffle_v16i16_u_u_u_u_u_u_u_u_3_3_3_3_3_3_3_3(<16 x i16> %a, <16 x i16> %b) {
+; AVX1-LABEL: shuffle_v16i16_u_u_u_u_u_u_u_u_3_3_3_3_3_3_3_3:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,7,6,7,6,7,6,7,6,7,6,7,6,7,6,7]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v16i16_u_u_u_u_u_u_u_u_3_3_3_3_3_3_3_3:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,7,6,7,6,7,6,7,6,7,6,7,6,7,6,7]
+; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
+ ret <16 x i16> %shuffle
+}
+
+define <16 x i16> @shuffle_v16i16_8_8_8_8_8_8_8_8_8_8_8_8_8_8_8_8(<16 x i16> %a, <16 x i16> %b) {
+; AVX1-LABEL: shuffle_v16i16_8_8_8_8_8_8_8_8_8_8_8_8_8_8_8_8:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v16i16_8_8_8_8_8_8_8_8_8_8_8_8_8_8_8_8:
+; AVX2: # BB#0:
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpbroadcastw %xmm0, %xmm0
+; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>
+ ret <16 x i16> %shuffle
+}
+
+define <16 x i16> @shuffle_v16i16_9_9_9_9_9_9_9_9_u_u_u_u_u_u_u_u(<16 x i16> %a, <16 x i16> %b) {
+; AVX1-LABEL: shuffle_v16i16_9_9_9_9_9_9_9_9_u_u_u_u_u_u_u_u:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,3,2,3,2,3,2,3,2,3,2,3,2,3,2,3]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v16i16_9_9_9_9_9_9_9_9_u_u_u_u_u_u_u_u:
+; AVX2: # BB#0:
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,3,2,3,2,3,2,3,2,3,2,3,2,3,2,3]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+ ret <16 x i16> %shuffle
+}
+
define <16 x i16> @insert_v16i16_0elt_into_zero_vector(i16* %ptr) {
; ALL-LABEL: insert_v16i16_0elt_into_zero_vector:
; ALL: # BB#0:
Modified: llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll?rev=253449&r1=253448&r2=253449&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll (original)
+++ llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll Wed Nov 18 03:39:38 2015
@@ -1977,6 +1977,57 @@ define <32 x i8> @shuffle_v32i8_15_00_01
ret <32 x i8> %shuffle
}
+define <32 x i8> @shuffle_v32i8_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_10_10_10_10_10_10_10_10_10_10_10_10_10_10_10_10(<32 x i8> %a, <32 x i8> %b) {
+; AVX1-LABEL: shuffle_v32i8_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_10_10_10_10_10_10_10_10_10_10_10_10_10_10_10_10:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v32i8_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_10_10_10_10_10_10_10_10_10_10_10_10_10_10_10_10:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10]
+; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10, i32 10>
+ ret <32 x i8> %shuffle
+}
+
+define <32 x i8> @shuffle_v32i8_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
+; AVX1-LABEL: shuffle_v32i8_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v32i8_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
+; AVX2: # BB#0:
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpbroadcastb %xmm0, %xmm0
+; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+ ret <32 x i8> %shuffle
+}
+
+define <32 x i8> @shuffle_v32i8_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu(<32 x i8> %a, <32 x i8> %b) {
+; AVX1-LABEL: shuffle_v32i8_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v32i8_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu:
+; AVX2: # BB#0:
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+ ret <32 x i8> %shuffle
+}
+
define <32 x i8> @insert_dup_mem_v32i8_i32(i32* %ptr) {
; AVX1-LABEL: insert_dup_mem_v32i8_i32:
; AVX1: # BB#0:
Modified: llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v4.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v4.ll?rev=253449&r1=253448&r2=253449&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v4.ll (original)
+++ llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v4.ll Wed Nov 18 03:39:38 2015
@@ -477,6 +477,56 @@ define <4 x double> @shuffle_v4f64_u062(
ret <4 x double> %shuffle
}
+define <4 x double> @shuffle_v4f64_11uu(<4 x double> %a, <4 x double> %b) {
+; ALL-LABEL: shuffle_v4f64_11uu:
+; ALL: # BB#0:
+; ALL-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 1, i32 undef, i32 undef>
+ ret <4 x double> %shuffle
+}
+
+define <4 x double> @shuffle_v4f64_22uu(<4 x double> %a, <4 x double> %b) {
+; AVX1-LABEL: shuffle_v4f64_22uu:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v4f64_22uu:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,3]
+; AVX2-NEXT: retq
+;
+; AVX512VL-LABEL: shuffle_v4f64_22uu:
+; AVX512VL: # BB#0:
+; AVX512VL-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,3]
+; AVX512VL-NEXT: retq
+ %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 2, i32 2, i32 undef, i32 undef>
+ ret <4 x double> %shuffle
+}
+
+define <4 x double> @shuffle_v4f64_3333(<4 x double> %a, <4 x double> %b) {
+; AVX1-LABEL: shuffle_v4f64_3333:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v4f64_3333:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[3,3,3,3]
+; AVX2-NEXT: retq
+;
+; AVX512VL-LABEL: shuffle_v4f64_3333:
+; AVX512VL: # BB#0:
+; AVX512VL-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[3,3,3,3]
+; AVX512VL-NEXT: retq
+ %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 3>
+ ret <4 x double> %shuffle
+}
+
define <4 x i64> @shuffle_v4i64_0000(<4 x i64> %a, <4 x i64> %b) {
; AVX1-LABEL: shuffle_v4i64_0000:
; AVX1: # BB#0:
@@ -1073,6 +1123,66 @@ define <4 x i64> @shuffle_v4i64_40u2(<4
ret <4 x i64> %shuffle
}
+define <4 x i64> @shuffle_v4i64_11uu(<4 x i64> %a, <4 x i64> %b) {
+; AVX1-LABEL: shuffle_v4i64_11uu:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v4i64_11uu:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[2,3,2,3,6,7,6,7]
+; AVX2-NEXT: retq
+;
+; AVX512VL-LABEL: shuffle_v4i64_11uu:
+; AVX512VL: # BB#0:
+; AVX512VL-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[2,3,2,3,6,7,6,7]
+; AVX512VL-NEXT: retq
+ %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 1, i32 undef, i32 undef>
+ ret <4 x i64> %shuffle
+}
+
+define <4 x i64> @shuffle_v4i64_22uu(<4 x i64> %a, <4 x i64> %b) {
+; AVX1-LABEL: shuffle_v4i64_22uu:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v4i64_22uu:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[2,2,2,3]
+; AVX2-NEXT: retq
+;
+; AVX512VL-LABEL: shuffle_v4i64_22uu:
+; AVX512VL: # BB#0:
+; AVX512VL-NEXT: vpermq {{.*#+}} ymm0 = ymm0[2,2,2,3]
+; AVX512VL-NEXT: retq
+ %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 2, i32 2, i32 undef, i32 undef>
+ ret <4 x i64> %shuffle
+}
+
+define <4 x i64> @shuffle_v4i64_3333(<4 x i64> %a, <4 x i64> %b) {
+; AVX1-LABEL: shuffle_v4i64_3333:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,1]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v4i64_3333:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,3,3,3]
+; AVX2-NEXT: retq
+;
+; AVX512VL-LABEL: shuffle_v4i64_3333:
+; AVX512VL: # BB#0:
+; AVX512VL-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,3,3,3]
+; AVX512VL-NEXT: retq
+ %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 3>
+ ret <4 x i64> %shuffle
+}
+
define <4 x i64> @stress_test1(<4 x i64> %a, <4 x i64> %b) {
; ALL-LABEL: stress_test1:
; ALL: retq
Modified: llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v8.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v8.ll?rev=253449&r1=253448&r2=253449&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v8.ll (original)
+++ llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v8.ll Wed Nov 18 03:39:38 2015
@@ -830,6 +830,55 @@ define <8 x float> @shuffle_v8f32_a2u3e6
ret <8 x float> %shuffle
}
+define <8 x float> @shuffle_v8f32_uuuu1111(<8 x float> %a, <8 x float> %b) {
+; AVX1-LABEL: shuffle_v8f32_uuuu1111:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8f32_uuuu1111:
+; AVX2: # BB#0:
+; AVX2-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
+; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 1, i32 1, i32 1>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_44444444(<8 x float> %a, <8 x float> %b) {
+; AVX1-LABEL: shuffle_v8f32_44444444:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8f32_44444444:
+; AVX2: # BB#0:
+; AVX2-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
+; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_5555uuuu(<8 x float> %a, <8 x float> %b) {
+; AVX1-LABEL: shuffle_v8f32_5555uuuu:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8f32_5555uuuu:
+; AVX2: # BB#0:
+; AVX2-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
+; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 undef, i32 undef, i32 undef, i32 undef>
+ ret <8 x float> %shuffle
+}
+
define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00000000:
; AVX1: # BB#0:
@@ -1895,6 +1944,55 @@ define <8 x i32> @shuffle_v8i32_80u1b4uu
ret <8 x i32> %shuffle
}
+define <8 x i32> @shuffle_v8i32_uuuu1111(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_uuuu1111:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_uuuu1111:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
+; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 1, i32 1, i32 1>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_44444444(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_44444444:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_44444444:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
+; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_5555uuuu(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_5555uuuu:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_5555uuuu:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
+; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 undef, i32 undef, i32 undef, i32 undef>
+ ret <8 x i32> %shuffle
+}
+
define <8 x float> @splat_mem_v8f32_2(float* %p) {
; ALL-LABEL: splat_mem_v8f32_2:
; ALL: # BB#0:
More information about the llvm-commits
mailing list