[NVPTX] Add missing patterns for div.approx with immediate denominator

[oota-llvm.git] / test / CodeGen / R600 / llvm.AMDGPU.mul.ll

diff --git a/test/CodeGen/R600/llvm.AMDGPU.mul.ll b/test/CodeGen/R600/llvm.AMDGPU.mul.ll
index 3c995c924f8cb1214f821d2d94b38c702334ccba..83b56a5029d36dbb01ae7d3a10aa6138c2934a2f 100644 (file)
--- a/test/CodeGen/R600/llvm.AMDGPU.mul.ll
+++ b/test/CodeGen/R600/llvm.AMDGPU.mul.ll
@@ -1,16 +1,17 @@
-;RUN: llc < %s -march=r600 -mcpu=redwood | diff %s.check -
+;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
 
+;CHECK: MUL NON-IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-define void @test() {
-   %r0 = call float @llvm.R600.load.input(i32 0)
-   %r1 = call float @llvm.R600.load.input(i32 1)
+define void @test(<4 x float> inreg %reg0) #0 {
+   %r0 = extractelement <4 x float> %reg0, i32 0
+   %r1 = extractelement <4 x float> %reg0, i32 1
    %r2 = call float @llvm.AMDGPU.mul( float %r0, float %r1)
-   call void @llvm.AMDGPU.store.output(float %r2, i32 0)
+   %vec = insertelement <4 x float> undef, float %r2, i32 0
+   call void @llvm.R600.store.swizzle(<4 x float> %vec, i32 0, i32 0)
    ret void
 }
 
-declare float @llvm.R600.load.input(i32) readnone
-
-declare void @llvm.AMDGPU.store.output(float, i32)
-
 declare float @llvm.AMDGPU.mul(float ,float ) readnone
+declare void @llvm.R600.store.swizzle(<4 x float>, i32, i32)
+
+attributes #0 = { "ShaderType"="0" }
\ No newline at end of file