Add isel patterns for v2f32 / v4f32 neon.vbsl intrinsics. rdar://12471808

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

diff --git a/test/CodeGen/ARM/reg_sequence.ll b/test/CodeGen/ARM/reg_sequence.ll
index 3a19211112802c0b543ba7642b3c95b92eb24977..6d6586e4f28397b780a64e9c291b79e1f9333953 100644 (file)
--- a/test/CodeGen/ARM/reg_sequence.ll
+++ b/test/CodeGen/ARM/reg_sequence.ll
@@ -1,5 +1,5 @@
-; RUN: llc < %s -march=arm -mcpu=cortex-a8 | FileCheck %s
-; RUN: llc < %s -march=arm -mcpu=cortex-a8 -regalloc=basic | FileCheck %s
+; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-a8 | FileCheck %s
+; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-a8 -regalloc=basic | FileCheck %s
 ; Implementing vld / vst as REG_SEQUENCE eliminates the extra vmov's.
 
 %struct.int16x8_t = type { <8 x i16> }
@@ -124,7 +124,6 @@ return1:
 return2:
 ; CHECK:        %return2
 ; CHECK:        vadd.i32
-; CHECK:        vorr {{q[0-9]+}}, {{q[0-9]+}}
 ; CHECK-NOT:    vmov
 ; CHECK:        vst2.32 {d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}}}
   %tmp100 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 0 ; <<4 x i32>> [#uses=1]
@@ -137,7 +136,7 @@ return2:
 
 define <8 x i16> @t5(i16* %A, <8 x i16>* %B) nounwind {
 ; CHECK:        t5:
-; CHECK:        vldmia
+; CHECK:        vld1.32
 ; How can FileCheck match Q and D registers? We need a lisp interpreter.
 ; CHECK:        vorr {{q[0-9]+}}, {{q[0-9]+}}, {{q[0-9]+}}
 ; CHECK-NOT:    vmov
@@ -155,7 +154,7 @@ define <8 x i16> @t5(i16* %A, <8 x i16>* %B) nounwind {
 
 define <8 x i8> @t6(i8* %A, <8 x i8>* %B) nounwind {
 ; CHECK:        t6:
-; CHECK:        vldr.64
+; CHECK:        vldr
 ; CHECK:        vorr d[[D0:[0-9]+]], d[[D1:[0-9]+]]
 ; CHECK-NEXT:   vld2.8 {d[[D1]][1], d[[D0]][1]}
   %tmp1 = load <8 x i8>* %B                       ; <<8 x i8>> [#uses=2]
@@ -240,11 +239,11 @@ bb14:                                             ; preds = %bb6
 ; PR7157
 define arm_aapcs_vfpcc float @t9(%0* nocapture, %3* nocapture) nounwind {
 ; CHECK:        t9:
-; CHECK:        vldr.64
+; CHECK:        vldr
 ; CHECK-NOT:    vmov d{{.*}}, d16
 ; CHECK:        vmov.i32 d17
-; CHECK-NEXT:   vstmia r0, {d16, d17}
-; CHECK-NEXT:   vstmia r0, {d16, d17}
+; CHECK-NEXT:   vst1.64 {d16, d17}, [r0, :128]
+; CHECK-NEXT:   vst1.64 {d16, d17}, [r0, :128]
   %3 = bitcast double 0.000000e+00 to <2 x float> ; <<2 x float>> [#uses=2]
   %4 = shufflevector <2 x float> %3, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> ; <<4 x float>> [#uses=1]
   store <4 x float> %4, <4 x float>* undef, align 16
@@ -272,8 +271,8 @@ define arm_aapcs_vfpcc float @t9(%0* nocapture, %3* nocapture) nounwind {
 define arm_aapcs_vfpcc i32 @t10() nounwind {
 entry:
 ; CHECK: t10:
-; CHECK: vmov.i32 q[[Q0:[0-9]+]], #0x3F000000
-; CHECK: vmul.f32 q8, q8, d0[0]
+; CHECK: vmov.i32 q[[Q0:[0-9]+]], #0x3f000000
+; CHECK: vmul.f32 q8, q8, d[[DREG:[0-1]+]]
 ; CHECK: vadd.f32 q8, q8, q8
   %0 = shufflevector <4 x float> zeroinitializer, <4 x float> undef, <4 x i32> zeroinitializer ; <<4 x float>> [#uses=1]
   %1 = insertelement <4 x float> %0, float undef, i32 1 ; <<4 x float>> [#uses=1]