[X86] Updated vector popcnt tests. Added vec512 tests.

[oota-llvm.git] / test / CodeGen / X86 / vector-popcnt-256.ll

diff --git a/test/CodeGen/X86/vector-popcnt-256.ll b/test/CodeGen/X86/vector-popcnt-256.ll
index 7ce4f712483a240cba665f34ef6f7faeffc61077..5f631832985a726167201bde73ec215b74c2d76e 100644 (file)
--- a/test/CodeGen/X86/vector-popcnt-256.ll
+++ b/test/CodeGen/X86/vector-popcnt-256.ll
@@ -1,9 +1,7 @@
-; RUN: llc < %s -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
-; RUN: llc < %s -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 
-target triple = "x86_64-unknown-unknown"
-
-define <4 x i64> @testv4i64(<4 x i64> %in) {
+define <4 x i64> @testv4i64(<4 x i64> %in) nounwind {
 ; AVX1-LABEL: testv4i64:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
@@ -44,7 +42,7 @@ define <4 x i64> @testv4i64(<4 x i64> %in) {
   ret <4 x i64> %out
 }
 
-define <8 x i32> @testv8i32(<8 x i32> %in) {
+define <8 x i32> @testv8i32(<8 x i32> %in) nounwind {
 ; AVX1-LABEL: testv8i32:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
@@ -97,7 +95,7 @@ define <8 x i32> @testv8i32(<8 x i32> %in) {
   ret <8 x i32> %out
 }
 
-define <16 x i16> @testv16i16(<16 x i16> %in) {
+define <16 x i16> @testv16i16(<16 x i16> %in) nounwind {
 ; AVX1-LABEL: testv16i16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
@@ -142,7 +140,7 @@ define <16 x i16> @testv16i16(<16 x i16> %in) {
   ret <16 x i16> %out
 }
 
-define <32 x i8> @testv32i8(<32 x i8> %in) {
+define <32 x i8> @testv32i8(<32 x i8> %in) nounwind {
 ; AVX1-LABEL: testv32i8:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
@@ -178,38 +176,38 @@ define <32 x i8> @testv32i8(<32 x i8> %in) {
   ret <32 x i8> %out
 }
 
-define <4 x i64> @foldv4i64() {
-; AVX-LABEL: foldv4i64:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [1,64,0,8]
-; AVX-NEXT:    retq
+define <4 x i64> @foldv4i64() nounwind {
+; ALL-LABEL: foldv4i64:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovaps {{.*#+}} ymm0 = [1,64,0,8]
+; ALL-NEXT:    retq
   %out = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> <i64 256, i64 -1, i64 0, i64 255>)
   ret <4 x i64> %out
 }
 
-define <8 x i32> @foldv8i32() {
-; AVX-LABEL: foldv8i32:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [1,32,0,8,16,3,2,3]
-; AVX-NEXT:    retq
+define <8 x i32> @foldv8i32() nounwind {
+; ALL-LABEL: foldv8i32:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovaps {{.*#+}} ymm0 = [1,32,0,8,16,3,2,3]
+; ALL-NEXT:    retq
   %out = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> <i32 256, i32 -1, i32 0, i32 255, i32 -65536, i32 7, i32 24, i32 88>)
   ret <8 x i32> %out
 }
 
-define <16 x i16> @foldv16i16() {
-; AVX-LABEL: foldv16i16:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [1,16,0,8,0,3,2,3,15,7,1,1,1,1,1,1]
-; AVX-NEXT:    retq
+define <16 x i16> @foldv16i16() nounwind {
+; ALL-LABEL: foldv16i16:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovaps {{.*#+}} ymm0 = [1,16,0,8,0,3,2,3,15,7,1,1,1,1,1,1]
+; ALL-NEXT:    retq
   %out = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> <i16 256, i16 -1, i16 0, i16 255, i16 -65536, i16 7, i16 24, i16 88, i16 -2, i16 254, i16 1, i16 2, i16 4, i16 8, i16 16, i16 32>)
   ret <16 x i16> %out
 }
 
-define <32 x i8> @foldv32i8() {
-; AVX-LABEL: foldv32i8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovaps {{.*#+}} ymm0 = [0,8,0,8,0,3,2,3,7,7,1,1,1,1,1,1,1,1,0,0,1,2,3,4,5,6,7,8,2,2,3,7]
-; AVX-NEXT:    retq
+define <32 x i8> @foldv32i8() nounwind {
+; ALL-LABEL: foldv32i8:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovaps {{.*#+}} ymm0 = [0,8,0,8,0,3,2,3,7,7,1,1,1,1,1,1,1,1,0,0,1,2,3,4,5,6,7,8,2,2,3,7]
+; ALL-NEXT:    retq
   %out = call <32 x i8> @llvm.ctpop.v32i8(<32 x i8> <i8 256, i8 -1, i8 0, i8 255, i8 -65536, i8 7, i8 24, i8 88, i8 -2, i8 254, i8 1, i8 2, i8 4, i8 8, i8 16, i8 32, i8 64, i8 128, i8 256, i8 -256, i8 -128, i8 -64, i8 -32, i8 -16, i8 -8, i8 -4, i8 -2, i8 -1, i8 3, i8 5, i8 7, i8 127>)
   ret <32 x i8> %out
 }