llvm/test/CodeGen/R600/fsub.ll
Vincent Lejeune 512119770e R600: Schedule copy from phys register at beginning of block
It allows regalloc pass to remove them by trivially assigning associated reg

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183336 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-05 20:27:35 +00:00

32 lines
1.0 KiB
LLVM

; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
; CHECK: @fsub_f32
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
define void @fsub_f32() {
%r0 = call float @llvm.R600.load.input(i32 0)
%r1 = call float @llvm.R600.load.input(i32 1)
%r2 = fsub float %r0, %r1
call void @llvm.AMDGPU.store.output(float %r2, i32 0)
ret void
}
declare float @llvm.R600.load.input(i32) readnone
declare void @llvm.AMDGPU.store.output(float, i32)
; CHECK: @fsub_v4f32
; CHECK: ADD T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: ADD * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define void @fsub_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
%b = load <4 x float> addrspace(1) * %b_ptr
%result = fsub <4 x float> %a, %b
store <4 x float> %result, <4 x float> addrspace(1)* %out
ret void
}