[x32] Fix FrameIndex check in SelectLEA64_32Addr

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

diff --git a/test/CodeGen/R600/fadd.ll b/test/CodeGen/R600/fadd.ll
index 874fcc6f43e510ba4badc5fd00219456304d4706..3a87c892d7ba71397b0d3fdc44c9c9be32dda4f2 100644 (file)
--- a/test/CodeGen/R600/fadd.ll
+++ b/test/CodeGen/R600/fadd.ll
@@ -1,15 +1,63 @@
-;RUN: llc < %s -march=r600 -mcpu=redwood | diff %s.check -
+; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
+; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck %s -check-prefix=SI -check-prefix=FUNC
 
-
-define void @test() {
-   %r0 = call float @llvm.R600.load.input(i32 0)
-   %r1 = call float @llvm.R600.load.input(i32 1)
-   %r2 = fadd float %r0, %r1
-   call void @llvm.AMDGPU.store.output(float %r2, i32 0)
+; FUNC-LABEL: @fadd_f32
+; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, KC0[2].W
+; SI: V_ADD_F32
+define void @fadd_f32(float addrspace(1)* %out, float %a, float %b) {
+   %add = fadd float %a, %b
+   store float %add, float addrspace(1)* %out, align 4
    ret void
 }
 
-declare float @llvm.R600.load.input(i32) readnone
+; FUNC-LABEL: @fadd_v2f32
+; R600-DAG: ADD {{\** *}}T{{[0-9]\.[XYZW]}}, KC0[3].X, KC0[3].Z
+; R600-DAG: ADD {{\** *}}T{{[0-9]\.[XYZW]}}, KC0[2].W, KC0[3].Y
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+define void @fadd_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
+  %add = fadd <2 x float> %a, %b
+  store <2 x float> %add, <2 x float> addrspace(1)* %out, align 8
+  ret void
+}
 
-declare void @llvm.AMDGPU.store.output(float, i32)
+; FUNC-LABEL: @fadd_v4f32
+; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+define void @fadd_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
+  %b_ptr = getelementptr <4 x float> addrspace(1)* %in, i32 1
+  %a = load <4 x float> addrspace(1)* %in, align 16
+  %b = load <4 x float> addrspace(1)* %b_ptr, align 16
+  %result = fadd <4 x float> %a, %b
+  store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
+  ret void
+}
 
+; FUNC-LABEL: @fadd_v8f32
+; R600: ADD
+; R600: ADD
+; R600: ADD
+; R600: ADD
+; R600: ADD
+; R600: ADD
+; R600: ADD
+; R600: ADD
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+; SI: V_ADD_F32
+define void @fadd_v8f32(<8 x float> addrspace(1)* %out, <8 x float> %a, <8 x float> %b) {
+  %add = fadd <8 x float> %a, %b
+  store <8 x float> %add, <8 x float> addrspace(1)* %out, align 32
+  ret void
+}