[llvm] c953e06 - [CodeGen] Increase the size of a SmallVector
Jay Foad via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 15 03:42:07 PST 2019
Author: Jay Foad
Date: 2019-11-15T11:32:11Z
New Revision: c953e061b410163bc54771f186176a92aac04008
URL: https://github.com/llvm/llvm-project/commit/c953e061b410163bc54771f186176a92aac04008
DIFF: https://github.com/llvm/llvm-project/commit/c953e061b410163bc54771f186176a92aac04008.diff
LOG: [CodeGen] Increase the size of a SmallVector
The SmallVector reserve() call in
MachineInstrExpressionTrait::getHashValue accounted for over 3% of all
calls to malloc() when I compiled a bunch of graphics shaders for the
AMDGPU target. Its initial size was only enough for machine instructions
with up to 7 operands, but for AMDGPU 8 and 10 operands are very common.
Here's a histogram of number of operands for each call to getHashValue,
gathered from the same collection of shaders:
1 13503
2 254273
3 135781
4 422508
5 614997
6 194953
7 287248
8 1517255
9 31218
10 1191269
11 70731
12 24
13 77
15 84
17 4692
27 16
33 705
49 6
Typical instructions with 8 and 10 operands are floating point
arithmetic and multiply-accumulate instructions like:
%83:vgpr_32 = V_MUL_F32_e64 0, killed %82:vgpr_32, 0, killed %81:vgpr_32, 0, 0, implicit $exec
%330:vgpr_32 = V_MAC_F32_e64 0, killed %327:vgpr_32, 0, killed %329:sgpr_32, 0, %328:vgpr_32(tied-def 0), 0, 0, implicit $exec
Differential Revision: https://reviews.llvm.org/D70301
Added:
Modified:
llvm/lib/CodeGen/MachineInstr.cpp
Removed:
################################################################################
diff --git a/llvm/lib/CodeGen/MachineInstr.cpp b/llvm/lib/CodeGen/MachineInstr.cpp
index 276a0a4aef6a..16ae732169a4 100644
--- a/llvm/lib/CodeGen/MachineInstr.cpp
+++ b/llvm/lib/CodeGen/MachineInstr.cpp
@@ -1977,7 +1977,7 @@ void MachineInstr::setPhysRegsDeadExcept(ArrayRef<Register> UsedRegs,
unsigned
MachineInstrExpressionTrait::getHashValue(const MachineInstr* const &MI) {
// Build up a buffer of hash code components.
- SmallVector<size_t, 8> HashComponents;
+ SmallVector<size_t, 16> HashComponents;
HashComponents.reserve(MI->getNumOperands() + 1);
HashComponents.push_back(MI->getOpcode());
for (const MachineOperand &MO : MI->operands()) {
More information about the llvm-commits
mailing list