Граф коммитов

9 Коммитов

Автор SHA1 Сообщение Дата
foreman a27a480c5f P4 to Git Change 1068415 by gandryey@gera-dev-w7 on 2014/08/20 10:41:55
ECR #304775 - Device enqueue
	- Fix a copy/paste typo with the "failure" argument

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#25 edit
2014-08-20 11:00:32 -04:00
foreman 8fa184db38 P4 to Git Change 1065597 by gandryey@gera-dev-w7 on 2014/08/12 18:38:45
ECR #304775 - Device enqueuing
	- Provide scratch buffer offset for generic address space
	- Use single scratch buffer for all available queues. Each queue will have a unique subbuffer in the global buffer

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#454 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#129 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusched.hpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#329 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#120 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.cpp#63 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.h#37 edit
2014-08-12 18:49:08 -04:00
foreman 3a4400135d P4 to Git Change 1059564 by gandryey@gera-dev-w7 on 2014/07/25 18:14:33
ECR #304775 - Device enqueuing
	- Run the scheduler in the host queue by default.
	- GPU_USE_DEVICE_QUEUE=1 can force execution in the device queue

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#451 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#128 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#260 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusched.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.cpp#273 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.hpp#86 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#327 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#119 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.cpp#62 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.h#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#208 edit
2014-07-25 20:41:05 -04:00
foreman d2b905f18e P4 to Git Change 1057998 by gandryey@gera-dev-w7 on 2014/07/22 17:15:58
ECR #304775 - Device enqueuing
	- Use atomic fetch for enqueue flags
	- Switch to a multithreaded scheduler
	- Add a workaround for Linux host_multi_queue failures. Linux has only 2 queues, but the test allocates multiple host queues and the same HW ring can be used

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#106 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#449 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#127 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#325 edit
2014-07-22 17:30:56 -04:00
foreman 6627cf5cf7 P4 to Git Change 1056280 by gandryey@gera-dev-w7 on 2014/07/17 11:55:30
ECR #304775 - Device enqueuing
	- Add extra sync point for the scheduler exit.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusched.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#323 edit
2014-07-17 12:20:49 -04:00
foreman 6314b334ba P4 to Git Change 1055054 by gandryey@gera-dev-w7 on 2014/07/14 20:18:53
ECR #304775 - Device enqueuing
	- Switch to the single thread scheduler for now(the current version isn't friendly for single thread). Hopefully it's a temporary solution until synchronization issue with multithreaded scheduler will be identified.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#104 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#20 edit
2014-07-14 20:24:58 -04:00
foreman 977f314094 P4 to Git Change 1053268 by gandryey@gera-dev-w7 on 2014/07/08 15:08:51
ECR #304775 - Device enqueuing
	- Add printing of the waiting events
	- Add early exit in the scheduler if nothing to launch

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#19 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#321 edit
2014-07-08 15:30:04 -04:00
foreman cd3fefb00d P4 to Git Change 1052832 by gandryey@gera-dev-w7 on 2014/07/07 18:44:29
ECR #304775 - Device enqueuing
	- Update the scheduler to handle event mask

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#320 edit
2014-07-07 18:58:52 -04:00
foreman 3694ab2ce8 initial commit 2014-07-04 16:17:05 -04:00