llvm-6502/test/CodeGen/R600/fabs.ll
Tom Stellard 8a6b7df6f8 R600: Expand vector FABS
NOTE: This is a candidate for the 3.4 branch.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@195881 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-27 21:23:39 +00:00

55 lines
1.9 KiB
LLVM

; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s --check-prefix=R600-CHECK
; RUN: llc < %s -march=r600 -mcpu=SI -verify-machineinstrs | FileCheck %s --check-prefix=SI-CHECK
; DAGCombiner will transform:
; (fabs (f32 bitcast (i32 a))) => (f32 bitcast (and (i32 a), 0x7FFFFFFF))
; unless isFabsFree returns true
; R600-CHECK-LABEL: @fabs_free
; R600-CHECK-NOT: AND
; R600-CHECK: |PV.{{[XYZW]}}|
; SI-CHECK-LABEL: @fabs_free
; SI-CHECK: V_ADD_F32_e64 v{{[0-9]}}, s{{[0-9]}}, 0, 1, 0, 0, 0
define void @fabs_free(float addrspace(1)* %out, i32 %in) {
entry:
%0 = bitcast i32 %in to float
%1 = call float @fabs(float %0)
store float %1, float addrspace(1)* %out
ret void
}
; R600-CHECK-LABEL: @fabs_v2
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
; SI-CHECK-LABEL: @fabs_v2
; SI-CHECK: V_ADD_F32_e64 v{{[0-9]}}, s{{[0-9]}}, 0, 1, 0, 0, 0
; SI-CHECK: V_ADD_F32_e64 v{{[0-9]}}, s{{[0-9]}}, 0, 1, 0, 0, 0
define void @fabs_v2(<2 x float> addrspace(1)* %out, <2 x float> %in) {
entry:
%0 = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
store <2 x float> %0, <2 x float> addrspace(1)* %out
ret void
}
; R600-CHECK-LABEL: @fabs_v4
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
; SI-CHECK-LABEL: @fabs_v4
; SI-CHECK: V_ADD_F32_e64 v{{[0-9]}}, s{{[0-9]}}, 0, 1, 0, 0, 0
; SI-CHECK: V_ADD_F32_e64 v{{[0-9]}}, s{{[0-9]}}, 0, 1, 0, 0, 0
; SI-CHECK: V_ADD_F32_e64 v{{[0-9]}}, s{{[0-9]}}, 0, 1, 0, 0, 0
; SI-CHECK: V_ADD_F32_e64 v{{[0-9]}}, s{{[0-9]}}, 0, 1, 0, 0, 0
define void @fabs_v4(<4 x float> addrspace(1)* %out, <4 x float> %in) {
entry:
%0 = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in)
store <4 x float> %0, <4 x float> addrspace(1)* %out
ret void
}
declare float @fabs(float ) readnone
declare <2 x float> @llvm.fabs.v2f32(<2 x float> ) readnone
declare <4 x float> @llvm.fabs.v4f32(<4 x float> ) readnone