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

[AMDGPU] Ask subtarget if waitcnt instruction is needed before barrier instruction 

Differential Revision: https://reviews.llvm.org/D24985

llvm-svn: 282875
This commit is contained in:
Konstantin Zhuravlyov 2016-09-30 16:50:36 +00:00
parent 51f514d853
commit d7bdf24f32
2 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
View File

@ -540,6 +540,12 @@ public:
/// Return the maximum number of waves per SIMD for kernels using \p VGPRs VGPRs /// Return the maximum number of waves per SIMD for kernels using \p VGPRs VGPRs
unsigned getOccupancyWithNumVGPRs(unsigned VGPRs) const; unsigned getOccupancyWithNumVGPRs(unsigned VGPRs) const;
/// \returns True if waitcnt instruction is needed before barrier instruction,
/// false otherwise.
bool needWaitcntBeforeBarrier() const {
return true;
}
}; };
} // End namespace llvm } // End namespace llvm

3
llvm/lib/Target/AMDGPU/SIInsertWaits.cpp
View File

@ -590,7 +590,8 @@ bool SIInsertWaits::runOnMachineFunction(MachineFunction &MF) {
// S_SENDMSG implicitly waits for all outstanding LGKM transfers to finish, // S_SENDMSG implicitly waits for all outstanding LGKM transfers to finish,
// but we also want to wait for any other outstanding transfers before // but we also want to wait for any other outstanding transfers before
// signalling other hardware blocks // signalling other hardware blocks
if (I->getOpcode() == AMDGPU::S_BARRIER || if ((I->getOpcode() == AMDGPU::S_BARRIER &&
ST->needWaitcntBeforeBarrier()) ||
I->getOpcode() == AMDGPU::S_SENDMSG) I->getOpcode() == AMDGPU::S_SENDMSG)
Required = LastIssued; Required = LastIssued;
else else