[X86][SSE] Added tests for i8/i16 vector shifts

[oota-llvm.git] / test / CodeGen / ARM / vselect_imax.ll

diff --git a/test/CodeGen/ARM/vselect_imax.ll b/test/CodeGen/ARM/vselect_imax.ll
index 9ea56a47bd23d360b748e83a29a2b93bc6d23160..0eb051036d996df88ee99dc830bf09b4e487d270 100644 (file)
--- a/test/CodeGen/ARM/vselect_imax.ll
+++ b/test/CodeGen/ARM/vselect_imax.ll
@@ -1,5 +1,5 @@
 ; RUN: opt < %s  -cost-model -analyze -mtriple=thumbv7-apple-ios6.0.0 -march=arm -mcpu=cortex-a8 | FileCheck %s --check-prefix=COST
-; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
+; RUN: llc -mtriple=arm-eabi -mattr=+neon %s -o - | FileCheck %s
 ; Make sure that ARM backend with NEON handles vselect.
 
 define void @vmax_v4i32(<4 x i32>* %m, <4 x i32> %a, <4 x i32> %b) {
@@ -18,8 +18,8 @@ define void @vmax_v4i32(<4 x i32>* %m, <4 x i32> %a, <4 x i32> %b) {
 ; CHECK-LABEL: func_blend10:
 define void @func_blend10(%T0_10* %loadaddr, %T0_10* %loadaddr2,
                            %T1_10* %blend, %T0_10* %storeaddr) {
-  %v0 = load %T0_10* %loadaddr
-  %v1 = load %T0_10* %loadaddr2
+  %v0 = load %T0_10, %T0_10* %loadaddr
+  %v1 = load %T0_10, %T0_10* %loadaddr2
   %c = icmp slt %T0_10 %v0, %v1
 ; CHECK: vbsl
 ; CHECK: vbsl
@@ -34,8 +34,8 @@ define void @func_blend10(%T0_10* %loadaddr, %T0_10* %loadaddr2,
 ; CHECK-LABEL: func_blend14:
 define void @func_blend14(%T0_14* %loadaddr, %T0_14* %loadaddr2,
                            %T1_14* %blend, %T0_14* %storeaddr) {
-  %v0 = load %T0_14* %loadaddr
-  %v1 = load %T0_14* %loadaddr2
+  %v0 = load %T0_14, %T0_14* %loadaddr
+  %v1 = load %T0_14, %T0_14* %loadaddr2
   %c = icmp slt %T0_14 %v0, %v1
 ; CHECK: vbsl
 ; CHECK: vbsl
@@ -52,8 +52,8 @@ define void @func_blend15(%T0_15* %loadaddr, %T0_15* %loadaddr2,
                            %T1_15* %blend, %T0_15* %storeaddr) {
 ; CHECK: vbsl
 ; CHECK: vbsl
-  %v0 = load %T0_15* %loadaddr
-  %v1 = load %T0_15* %loadaddr2
+  %v0 = load %T0_15, %T0_15* %loadaddr
+  %v1 = load %T0_15, %T0_15* %loadaddr2
   %c = icmp slt %T0_15 %v0, %v1
 ; COST: func_blend15
 ; COST: cost of 82 {{.*}} select
@@ -68,8 +68,8 @@ define void @func_blend18(%T0_18* %loadaddr, %T0_18* %loadaddr2,
                            %T1_18* %blend, %T0_18* %storeaddr) {
 ; CHECK: vbsl
 ; CHECK: vbsl
-  %v0 = load %T0_18* %loadaddr
-  %v1 = load %T0_18* %loadaddr2
+  %v0 = load %T0_18, %T0_18* %loadaddr
+  %v1 = load %T0_18, %T0_18* %loadaddr2
   %c = icmp slt %T0_18 %v0, %v1
 ; COST: func_blend18
 ; COST: cost of 19 {{.*}} select
@@ -86,8 +86,8 @@ define void @func_blend19(%T0_19* %loadaddr, %T0_19* %loadaddr2,
 ; CHECK: vbsl
 ; CHECK: vbsl
 ; CHECK: vbsl
-  %v0 = load %T0_19* %loadaddr
-  %v1 = load %T0_19* %loadaddr2
+  %v0 = load %T0_19, %T0_19* %loadaddr
+  %v1 = load %T0_19, %T0_19* %loadaddr2
   %c = icmp slt %T0_19 %v0, %v1
 ; COST: func_blend19
 ; COST: cost of 50 {{.*}} select
@@ -108,8 +108,8 @@ define void @func_blend20(%T0_20* %loadaddr, %T0_20* %loadaddr2,
 ; CHECK: vbsl
 ; CHECK: vbsl
 ; CHECK: vbsl
-  %v0 = load %T0_20* %loadaddr
-  %v1 = load %T0_20* %loadaddr2
+  %v0 = load %T0_20, %T0_20* %loadaddr
+  %v1 = load %T0_20, %T0_20* %loadaddr2
   %c = icmp slt %T0_20 %v0, %v1
 ; COST: func_blend20
 ; COST: cost of 100 {{.*}} select