mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
dd292a30dc
Detailed description:
After https://reviews.llvm.org/D59990 submit several issues were discovered.
Changes in common code were preserved but AMDGPU specific part was reverted to keep the backend working correctly.
Discovered issues were addressed in the following commits:
https://reviews.llvm.org/D67662
https://reviews.llvm.org/D67101
https://reviews.llvm.org/D63953
https://reviews.llvm.org/D63731
This change brings back AMDGPU specific changes.
Reviewed by: rampitec, arsenm
Differential Revision: https://reviews.llvm.org/D68635
llvm-svn: 374767
114 lines
4.4 KiB
LLVM
114 lines
4.4 KiB
LLVM
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=FUNC %s
|
|
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}fneg_fabs_fadd_f32:
|
|
; SI-NOT: and
|
|
; SI: v_sub_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, |{{v[0-9]+}}|
|
|
define amdgpu_kernel void @fneg_fabs_fadd_f32(float addrspace(1)* %out, float %x, float %y) {
|
|
%fabs = call float @llvm.fabs.f32(float %x)
|
|
%fsub = fsub float -0.000000e+00, %fabs
|
|
%fadd = fadd float %y, %fsub
|
|
store float %fadd, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fneg_fabs_fmul_f32:
|
|
; SI-NOT: and
|
|
; SI: v_mul_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, -|{{v[0-9]+}}|
|
|
; SI-NOT: and
|
|
define amdgpu_kernel void @fneg_fabs_fmul_f32(float addrspace(1)* %out, float %x, float %y) {
|
|
%fabs = call float @llvm.fabs.f32(float %x)
|
|
%fsub = fsub float -0.000000e+00, %fabs
|
|
%fmul = fmul float %y, %fsub
|
|
store float %fmul, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; DAGCombiner will transform:
|
|
; (fabs (f32 bitcast (i32 a))) => (f32 bitcast (and (i32 a), 0x7FFFFFFF))
|
|
; unless isFabsFree returns true
|
|
|
|
; FUNC-LABEL: {{^}}fneg_fabs_free_f32:
|
|
; R600-NOT: AND
|
|
; R600: |PV.{{[XYZW]}}|
|
|
; R600: -PV
|
|
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
|
|
; VI: s_bitset1_b32 s{{[0-9]+}}, 31
|
|
define amdgpu_kernel void @fneg_fabs_free_f32(float addrspace(1)* %out, i32 %in) {
|
|
%bc = bitcast i32 %in to float
|
|
%fabs = call float @llvm.fabs.f32(float %bc)
|
|
%fsub = fsub float -0.000000e+00, %fabs
|
|
store float %fsub, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fneg_fabs_fn_free_f32:
|
|
; R600-NOT: AND
|
|
; R600: |PV.{{[XYZW]}}|
|
|
; R600: -PV
|
|
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
|
|
define amdgpu_kernel void @fneg_fabs_fn_free_f32(float addrspace(1)* %out, i32 %in) {
|
|
%bc = bitcast i32 %in to float
|
|
%fabs = call float @fabs(float %bc)
|
|
%fsub = fsub float -0.000000e+00, %fabs
|
|
store float %fsub, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fneg_fabs_f32:
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
|
|
define amdgpu_kernel void @fneg_fabs_f32(float addrspace(1)* %out, float %in) {
|
|
%fabs = call float @llvm.fabs.f32(float %in)
|
|
%fsub = fsub float -0.000000e+00, %fabs
|
|
store float %fsub, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_fneg_fabs_f32:
|
|
; SI: v_or_b32_e32 v{{[0-9]+}}, 0x80000000, v{{[0-9]+}}
|
|
define amdgpu_kernel void @v_fneg_fabs_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
|
|
%val = load float, float addrspace(1)* %in, align 4
|
|
%fabs = call float @llvm.fabs.f32(float %val)
|
|
%fsub = fsub float -0.000000e+00, %fabs
|
|
store float %fsub, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fneg_fabs_v2f32:
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600: -PV
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600: -PV
|
|
|
|
; FIXME: In this case two uses of the constant should be folded
|
|
; SI: s_brev_b32 [[SIGNBITK:s[0-9]+]], 1{{$}}
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
|
|
define amdgpu_kernel void @fneg_fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) {
|
|
%fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
|
|
%fsub = fsub <2 x float> <float -0.000000e+00, float -0.000000e+00>, %fabs
|
|
store <2 x float> %fsub, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fneg_fabs_v4f32:
|
|
; SI: s_brev_b32 [[SIGNBITK:s[0-9]+]], 1{{$}}
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
|
|
; SI: s_or_b32 s{{[0-9]+}}, s{{[0-9]+}}, [[SIGNBITK]]
|
|
define amdgpu_kernel void @fneg_fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) {
|
|
%fabs = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in)
|
|
%fsub = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %fabs
|
|
store <4 x float> %fsub, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare float @fabs(float) readnone
|
|
declare float @llvm.fabs.f32(float) readnone
|
|
declare <2 x float> @llvm.fabs.v2f32(<2 x float>) readnone
|
|
declare <4 x float> @llvm.fabs.v4f32(<4 x float>) readnone
|