mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-22 07:32:48 +00:00
de2e0bc366
V_ADD_F32 with source modifier does not produce -0.0 for this. Just manipulate the sign bit directly instead. Also add a pattern for (fneg (fabs ...)). Fixes a bunch of bit encoding piglit tests with radeonsi. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200743 91177308-0d34-0410-b5e6-96231b3b80d8
56 lines
1.8 KiB
LLVM
56 lines
1.8 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: @fneg_fabs_free
|
|
; R600-CHECK-NOT: AND
|
|
; R600-CHECK: |PV.{{[XYZW]}}|
|
|
; R600-CHECK: -PV
|
|
; SI-CHECK-LABEL: @fneg_fabs_free
|
|
; SI-CHECK: V_OR_B32
|
|
|
|
define void @fneg_fabs_free(float addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%0 = bitcast i32 %in to float
|
|
%1 = call float @fabs(float %0)
|
|
%2 = fsub float -0.000000e+00, %1
|
|
store float %2, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; R600-CHECK-LABEL: @fneg_fabs_v2
|
|
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600-CHECK: -PV
|
|
; R600-CHECK: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600-CHECK: -PV
|
|
; SI-CHECK-LABEL: @fneg_fabs_v2
|
|
; SI-CHECK: V_OR_B32
|
|
; SI-CHECK: V_OR_B32
|
|
define void @fneg_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)
|
|
%1 = fsub <2 x float> <float -0.000000e+00, float -0.000000e+00>, %0
|
|
store <2 x float> %1, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SI-CHECK-LABEL: @fneg_fabs_v4
|
|
; SI-CHECK: V_OR_B32
|
|
; SI-CHECK: V_OR_B32
|
|
; SI-CHECK: V_OR_B32
|
|
; SI-CHECK: V_OR_B32
|
|
define void @fneg_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)
|
|
%1 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
|
|
store <4 x float> %1, <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
|