foreman c0087b3b65 P4 to Git Change 1104993 by gandryey@gera-ubuntu14 on 2014/12/12 12:19:20 ...

EPR #410797 - Specific OCL kernel is 5x slower on Hawaii than on Nvidia K40 GPU when tested under Linux.
	- The logic for local workgroup size search was prioritizing ALU utilization, but with multidemensional launches X dimension could affect address calculation and cacheline utlization more than others. Add cacheline size into the consideration.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#270 edit


[ROCm/clr commit: 674da4560d]

2014-12-12 12:26:52 -05:00

projects/clr/rocclr

P4 to Git Change 1104993 by gandryey@gera-ubuntu14 on 2014/12/12 12:19:20

2014-12-12 12:26:52 -05:00

S

Описание

No description provided

282 MiB

Languages

C++ 67.5%

C 20.6%

Python 6.6%

CMake 3.4%

Shell 0.6%

Разное 1.1%