1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming
Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236
[ROCm/hip-tests commit: 7735b454a1]
1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming
Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236
1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming
Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236
[ROCm/clr commit: 1cead6a4cd]
1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming
Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236
1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming
Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236
[ROCm/hip commit: b9091ba818]
1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming
Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236
SWDEV-2 - Change OpenCL version number from 2393 to 2394.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2140 edit
[ROCm/clr commit: 89b8c47c24]
SWDEV-2 - Change OpenCL version number from 2393 to 2394.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2140 edit
SWDEV-115408 - [Vega10] IB size mismatch in OCL submissions
- Incorrect result for OS event wait was causing this issue, because runtime could overwrite an incomplete IB. A workaround is to check TS value after a wait returned a successful code
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#266 edit
[ROCm/clr commit: 39290bb733]
SWDEV-115408 - [Vega10] IB size mismatch in OCL submissions
- Incorrect result for OS event wait was causing this issue, because runtime could overwrite an incomplete IB. A workaround is to check TS value after a wait returned a successful code
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#266 edit
SWDEV-79278 - [OpenCL][GFXIP9 Bring up] Add the Vega10 DeviceInfo entry and the gfx90X control functions.
- modify getHsaDeviceId() to use HSA_AGENT_INFO_NAME to determine the HSA device ID.
- add back the codes to get the pci_id in the function
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#46 edit
[ROCm/clr commit: 37f3408aef]
SWDEV-79278 - [OpenCL][GFXIP9 Bring up] Add the Vega10 DeviceInfo entry and the gfx90X control functions.
- modify getHsaDeviceId() to use HSA_AGENT_INFO_NAME to determine the HSA device ID.
- add back the codes to get the pci_id in the function
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#46 edit
SWDEV-79278 - [OpenCL][GFXIP9 Bring up] Add the Vega10 DeviceInfo entry and the gfx90X control functions.
- modify getHsaDeviceId() to use HSA_AGENT_INFO_NAME to determine the HSA device ID.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#45 edit
[ROCm/clr commit: 168c0a27b7]
SWDEV-79278 - [OpenCL][GFXIP9 Bring up] Add the Vega10 DeviceInfo entry and the gfx90X control functions.
- modify getHsaDeviceId() to use HSA_AGENT_INFO_NAME to determine the HSA device ID.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#45 edit
Guard pages help catch out-of-bounds memory accesses by applications
by generating VM faults (GPU) and segfaults (CPU).
Remove address space reservation from scratch aperture. That address
space is managed by the Thunk client. Guard pages would cause Thunk's
address space management to get out of sync with the client's.
Change-Id: I2e5aee2923a90186358cc7b0e131baf547996df6
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Guard pages help catch out-of-bounds memory accesses by applications
by generating VM faults (GPU) and segfaults (CPU).
Remove address space reservation from scratch aperture. That address
space is managed by the Thunk client. Guard pages would cause Thunk's
address space management to get out of sync with the client's.
Change-Id: I2e5aee2923a90186358cc7b0e131baf547996df6
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
[ROCm/ROCR-Runtime commit: 11862b9f61]
SWDEV-2 - Change OpenCL version number from 2392 to 2393.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2139 edit
[ROCm/clr commit: c6b63501b4]
SWDEV-2 - Change OpenCL version number from 2392 to 2393.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2139 edit
SWDEV-116959 - ROCm OpenCL: split -amdgpu-internalize-symbols and -amdgpu-early-inline-all
We shall not run internalize pass in FE, it breaks separate compilation.
Thus two options are split now.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#61 edit
[ROCm/clr commit: a831af4af0]
SWDEV-116959 - ROCm OpenCL: split -amdgpu-internalize-symbols and -amdgpu-early-inline-all
We shall not run internalize pass in FE, it breaks separate compilation.
Thus two options are split now.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#61 edit
Aditya Atluri
foreman
Sun, Peng
Felix Kuehling
emankov