6eaad1e539
Summary: I had a case where multiple nested uniform ifs resulted in code that did v_cmp comparisons, combining the results with s_and_b64, s_or_b64 and s_xor_b64 and using the resulting mask in s_cbranch_vccnz, without first ensuring that bits for inactive lanes were clear. There was already code for inserting an "s_and_b64 vcc, exec, vcc" to clear bits for inactive lanes in the case that the branch is instruction selected as s_cbranch_scc1 and is then changed to s_cbranch_vccnz in SIFixSGPRCopies. I have added the same code into SILowerControlFlow for the case that the branch is instruction selected as s_cbranch_vccnz. This de-optimizes the code in some cases where the s_and is not needed, because vcc is the result of a v_cmp, or multiple v_cmp instructions combined by s_and/s_or. We should add a pass to re-optimize those cases. Reviewers: arsenm, kzhuravl Subscribers: wdng, yaxunl, t-tye, llvm-commits, dstuttard, timcorringham, nhaehnle Differential Revision: https://reviews.llvm.org/D41292 llvm-svn: 322119
48 lines
1.6 KiB
LLVM
48 lines
1.6 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VCCZ-BUG %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VCCZ-BUG %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=NOVCCZ-BUG %s
|
|
|
|
; GCN-FUNC: {{^}}vccz_workaround:
|
|
; GCN: s_load_dword s{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0x0
|
|
; GCN: v_cmp_neq_f32_e64 {{[^,]*}}, s{{[0-9]+}}, 0{{$}}
|
|
; VCCZ-BUG: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; VCCZ-BUG: s_mov_b64 vcc, vcc
|
|
; NOVCCZ-BUG-NOT: s_mov_b64 vcc, vcc
|
|
; GCN: s_cbranch_vccnz [[EXIT:[0-9A-Za-z_]+]]
|
|
; GCN: buffer_store_dword
|
|
; GCN: [[EXIT]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @vccz_workaround(i32 addrspace(2)* %in, i32 addrspace(1)* %out, float %cond) {
|
|
entry:
|
|
%cnd = fcmp oeq float 0.0, %cond
|
|
%sgpr = load volatile i32, i32 addrspace(2)* %in
|
|
br i1 %cnd, label %if, label %endif
|
|
|
|
if:
|
|
store i32 %sgpr, i32 addrspace(1)* %out
|
|
br label %endif
|
|
|
|
endif:
|
|
ret void
|
|
}
|
|
|
|
; GCN-FUNC: {{^}}vccz_noworkaround:
|
|
; GCN: v_cmp_neq_f32_e32 vcc, 0, v{{[0-9]+}}
|
|
; GCN: s_cbranch_vccnz [[EXIT:[0-9A-Za-z_]+]]
|
|
; GCN: buffer_store_dword
|
|
; GCN: [[EXIT]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @vccz_noworkaround(float addrspace(1)* %in, float addrspace(1)* %out) {
|
|
entry:
|
|
%vgpr = load volatile float, float addrspace(1)* %in
|
|
%cnd = fcmp oeq float 0.0, %vgpr
|
|
br i1 %cnd, label %if, label %endif
|
|
|
|
if:
|
|
store float %vgpr, float addrspace(1)* %out
|
|
br label %endif
|
|
|
|
endif:
|
|
ret void
|
|
}
|