AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

P4 to Git Change 1226881 by wchau@wchau_WIN_OCL_HSA on 2016/01/12 14:03:39

Browse Source 
SWDEV-79308 -  Reduce the total scratch buffer size by a factor of 4, which in effect reducing the max. scratch waves from 32 to 8, to avoid the required total scratch buffer
	size exceeds the available local memory.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#152 edit
This commit is contained in:
foreman
2016-01-12 14:11:46 -05:00
parent 6a0e72acc5
commit a319c0e35c
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rocclr/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp
+7
View File
@@ -1231,6 +1231,13 @@ CALGSLDevice::calcScratchBufferSize(uint32 regNum) const
m_cs->CalcAllScratchBufferSizes(enabledShadersFlag, scratchSpacePerShaderStage,
scratchBufferSizes);
// SWDEV-79308:
// Reduce the total scratch buffer size by a factor of 4, which in effect reducing the
// max. scratch waves from 32 to 8. This will avoid the required total scratch buffer
// size exceeds the available local memory.
scratchBufferSizes[target] >>= 2;
return scratchBufferSizes[target];
}