maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/select-fabs-fneg-extract-le...

47 lines
1.9 KiB
LLVM
Raw Normal View History

AMDGPU: Skip fneg/select combine if it can fold into other llvm-svn: 291792
2017-01-13 02:58:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
; --------------------------------------------------------------------------------
; Don't fold if fneg can fold into the source
; --------------------------------------------------------------------------------
; GCN-LABEL: {{^}}select_fneg_posk_src_rcp_legacy_f32:
; GCN: buffer_load_dword [[X:v[0-9]+]]
; GCN: v_rcp_legacy_f32_e32 [[RCP:v[0-9]+]], [[X]]
; GCN: v_cndmask_b32_e32 [[SELECT:v[0-9]+]], -2.0, [[RCP]], vcc
; GCN: v_xor_b32_e32 [[NEG_SELECT:v[0-9]+]], 0x80000000, [[SELECT]]
; GCN-NEXT: buffer_store_dword [[NEG_SELECT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @select_fneg_posk_src_rcp_legacy_f32(i32 %c) #2 {
AMDGPU: Skip fneg/select combine if it can fold into other llvm-svn: 291792
2017-01-13 02:58:15 +08:00
%x = load volatile float, float addrspace(1)* undef
%y = load volatile float, float addrspace(1)* undef
%cmp = icmp eq i32 %c, 0
%rcp = call float @llvm.amdgcn.rcp.legacy(float %x)
%fneg = fsub float -0.0, %rcp
%select = select i1 %cmp, float %fneg, float 2.0
store volatile float %select, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}select_fneg_posk_src_mul_legacy_f32:
; GCN: buffer_load_dword [[X:v[0-9]+]]
; GCN: v_mul_legacy_f32_e32 [[MUL:v[0-9]+]], 4.0, [[X]]
; GCN: v_cndmask_b32_e32 [[SELECT:v[0-9]+]], -2.0, [[MUL]], vcc
; GCN: v_xor_b32_e32 [[NEG_SELECT:v[0-9]+]], 0x80000000, [[SELECT]]
; GCN-NEXT: buffer_store_dword [[NEG_SELECT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @select_fneg_posk_src_mul_legacy_f32(i32 %c) #2 {
AMDGPU: Skip fneg/select combine if it can fold into other llvm-svn: 291792
2017-01-13 02:58:15 +08:00
%x = load volatile float, float addrspace(1)* undef
%cmp = icmp eq i32 %c, 0
%mul = call float @llvm.amdgcn.fmul.legacy(float %x, float 4.0)
%fneg = fsub float -0.0, %mul
%select = select i1 %cmp, float %fneg, float 2.0
store volatile float %select, float addrspace(1)* undef
ret void
}
declare float @llvm.amdgcn.rcp.legacy(float) #1
declare float @llvm.amdgcn.fmul.legacy(float, float) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }