1bad00adc4
This is a followup to https://github.com/llvm/llvm-project/pull/171288, which removed lowering of libcalls to SDAG nodes for most libcalls that get unconditionally canonicalized to intrinsics. This handles the remaining fabs case, which I originally skipped due to larger test impact.
18 lines
552 B
LLVM
18 lines
552 B
LLVM
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
|
|
|
|
; CHECK: {{^}}main:
|
|
; CHECK-NOT: MOV
|
|
define amdgpu_ps void @main(<4 x float> inreg %reg0) {
|
|
entry:
|
|
%0 = extractelement <4 x float> %reg0, i32 0
|
|
%1 = call float @llvm.fabs.f32(float %0)
|
|
%2 = fptoui float %1 to i32
|
|
%3 = bitcast i32 %2 to float
|
|
%4 = insertelement <4 x float> poison, float %3, i32 0
|
|
call void @llvm.r600.store.swizzle(<4 x float> %4, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.fabs.f32(float ) readnone
|
|
declare void @llvm.r600.store.swizzle(<4 x float>, i32, i32)
|