maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] Fix scalar operand folding bug that causes SHOC performance regression. 

Detailed description: SIFoldOperands::foldInstOperand iterates over the
operand uses calling the function that changes def-use iteratorson the
way. As a result loop exits immediately when def-use iterator is
changed. Hence, the operand is folded to the very first use instruction
only. This makes VGPR live along the whole basic block and increases
register pressure significantly. The performance drop observed in SHOC
DeviceMemory test is caused by this bug.

Proposed fix: collect uses to separate container for further processing
in another loop.

Testing: make check-llvm
SHOC performance test.

Reviewers: rampitec, ronlieb

Differential Revision: https://reviews.llvm.org/D56161

llvm-svn: 350350
This commit is contained in:
Alexander Timofeev 2019-01-03 19:55:32 +00:00
parent a470aa6701
commit 993e2798fd
2 changed files with 17 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View File

@ -854,13 +854,17 @@ void SIFoldOperands::foldInstOperand(MachineInstr &MI,
}
} else {
// Folding register.
SmallVector <MachineRegisterInfo::use_iterator, 4> UsesToProcess;
for (MachineRegisterInfo::use_iterator
Use = MRI->use_begin(Dst.getReg()), E = MRI->use_end();
Use != E; ++Use) {
MachineInstr *UseMI = Use->getParent();
UsesToProcess.push_back(Use);
}
for (auto U : UsesToProcess) {
MachineInstr *UseMI = U->getParent();
foldOperand(OpToFold, UseMI, Use.getOperandNo(),
FoldList, CopiesToReplace);
foldOperand(OpToFold, UseMI, U.getOperandNo(),
FoldList, CopiesToReplace);
}
}

20
llvm/test/CodeGen/AMDGPU/fdiv32-to-rcp-folding.ll
View File

@ -131,10 +131,10 @@ define amdgpu_kernel void @div_v4_1_by_x_25ulp(<4 x float> addrspace(1)* %arg) {
; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_rcp_f32_e32
; GCN-DENORM-DAG: v_rcp_f32_e32
; GCN-DENORM-DAG: v_rcp_f32_e32
@ -166,10 +166,10 @@ define amdgpu_kernel void @div_v4_minus_1_by_x_25ulp(<4 x float> addrspace(1)* %
; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
; GCN-DENORM-DAG: v_cmp_gt_f32_e64 vcc, |v{{[0-9]+}}|, [[L]]
; GCN-DENORM-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_rcp_f32_e32
; GCN-DENORM-DAG: v_rcp_f32_e32
; GCN-DENORM-DAG: v_rcp_f32_e32
@ -246,7 +246,7 @@ define amdgpu_kernel void @div_v4_minus_1_by_minus_x_25ulp(<4 x float> addrspace
; GCN-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, -v{{[0-9]+}}
; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP1:v[0-9]+]], v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, [[RCP1]]
; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP2:v[0-9]+]], v{{[0-9]+}}
@ -288,7 +288,7 @@ define amdgpu_kernel void @div_v4_c_by_x_25ulp(<4 x float> addrspace(1)* %arg) {
; GCN-DAG: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, [[S]], vcc
; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e64 v{{[0-9]+}}, -s{{[0-9]+}}, v{{[0-9]+}}
; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP1:v[0-9]+]], v{{[0-9]+}}
; GCN-DENORM-DAG: v_mul_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, [[RCP1]]
; GCN-DENORM-DAG: v_rcp_f32_e32 [[RCP2:v[0-9]+]], v{{[0-9]+}}