diff options
| author | Marek Olsak <marek.olsak@amd.com> | 2016-07-13 17:35:15 +0000 |
|---|---|---|
| committer | Marek Olsak <marek.olsak@amd.com> | 2016-07-13 17:35:15 +0000 |
| commit | 0532c190f7b0a8c33fdc20485c23815e2321bd16 (patch) | |
| tree | fe55f36ca26b2aecdc9b0ea7172f35ceabacf5da /llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp | |
| parent | 1852a784161c6a61ff1446e267c5e459f2c2a268 (diff) | |
| download | bcm5719-llvm-0532c190f7b0a8c33fdc20485c23815e2321bd16.tar.gz bcm5719-llvm-0532c190f7b0a8c33fdc20485c23815e2321bd16.zip | |
AMDGPU/SI: Emit the number of SGPR and VGPR spills
Summary:
v2: don't count SGPRs spilled to scratch twice
I think this is sufficient. It doesn't count private memory usage, which
happens often and uses scratch but isn't technically a spill. The private
memory usage can be computed by:
[scratch_per_thread - vgpr_spills - a random multiple of SGPR spills].
The fact SGPR spills add very high numbers to the scratch size make that
computation a guessing game, but I don't have a solution to that.
Reviewers: tstellarAMD
Subscribers: arsenm, kzhuravl
Differential Revision: http://reviews.llvm.org/D22197
llvm-svn: 275288
Diffstat (limited to 'llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp index 2c478d5213e..4d12a1ef9a9 100644 --- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp +++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp @@ -63,6 +63,8 @@ SIMachineFunctionInfo::SIMachineFunctionInfo(const MachineFunction &MF) HasSpilledVGPRs(false), HasNonSpillStackObjects(false), HasFlatInstructions(false), + NumSpilledSGPRs(0), + NumSpilledVGPRs(0), PrivateSegmentBuffer(false), DispatchPtr(false), QueuePtr(false), |
