RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
Code Issues Projects Releases Wiki Activity

Reverse subregister saved loops in register usage info collector; NFC

Browse Source 
On AMDGPU we have 70 register classes, so iterating over all 70
each time and exiting is costly on the CPU, this flips the loop
around so that it loops over the 70 register classes first,
and exits without doing the inner loop if needed.

On my test just starting radv this takes
RegUsageInfoCollector::runOnMachineFunction
from 6.0% of total time to 2.7% of total time,
and reduces the startup from 2.24s to 2.19s

Patch by David Airlie!

Differential Revision: https://reviews.llvm.org/D48582

llvm-svn: 340993
This commit is contained in:
Matthias Braun 2018-08-29 23:12:42 +00:00
parent ddf31c570a
commit a9707dee3c
1 changed files with 20 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
lib/CodeGen/RegUsageInfoCollector.cpp
View File

@ -166,28 +166,27 @@ computeCalleeSavedRegs(BitVector &SavedRegs, MachineFunction &MF) {
}
// Insert any register fully saved via subregisters.
for (unsigned PReg = 1, PRegE = TRI.getNumRegs(); PReg < PRegE; ++PReg) {
if (SavedRegs.test(PReg))
continue;
for (const TargetRegisterClass *RC : TRI.regclasses()) {
if (!RC->CoveredBySubRegs)
continue;
// Check if PReg is fully covered by its subregs.
bool CoveredBySubRegs = false;
for (const TargetRegisterClass *RC : TRI.regclasses())
if (RC->CoveredBySubRegs && RC->contains(PReg)) {
CoveredBySubRegs = true;
break;
}
if (!CoveredBySubRegs)
continue;
for (unsigned PReg = 1, PRegE = TRI.getNumRegs(); PReg < PRegE; ++PReg) {
if (SavedRegs.test(PReg))
continue;
// Add PReg to SavedRegs if all subregs are saved.
bool AllSubRegsSaved = true;
for (MCSubRegIterator SR(PReg, &TRI, false); SR.isValid(); ++SR)
if (!SavedRegs.test(*SR)) {
AllSubRegsSaved = false;
break;
}
if (AllSubRegsSaved)
SavedRegs.set(PReg);
// Check if PReg is fully covered by its subregs.
if (!RC->contains(PReg))
continue;
// Add PReg to SavedRegs if all subregs are saved.
bool AllSubRegsSaved = true;
for (MCSubRegIterator SR(PReg, &TRI, false); SR.isValid(); ++SR)
if (!SavedRegs.test(*SR)) {
AllSubRegsSaved = false;
break;
}
if (AllSubRegsSaved)
SavedRegs.set(PReg);
}
}
}