The current texture implementation is based off the one for HIP-HCC. There's a lot of problems with it - only creating images from buffers, hard coding logic and ignoring user parameters. This leads to a whole lot of UB even with simple examples (as seen with RedShift's code).
This CL is aimed to bring the HIP-VDI texture implementation closer to what is described by Cuda.
hipMemcpyAtoA() - image to image copy.
hipMemcpyHtoA()/hipMemcpyDtoA() - buffer to image copy.
hipMemcpyAtoH()/hipMemcpyAtoD() - image to buffer copy.
hipArrayCreate()/hipArray3DCreate()/hipMallocArray()/hipMalloc3DArray() - creates 1D/2D/3D/1D Array/2D Array images.
hipCreateTextureObject() - creates sampler, (optional) creates 1D/2D image from buffer, (optional) creates image views.
hipBindTexture() - creates 1D image from buffer (should create a typed buffer, however this is not compatible with HIP-HCC).
hipBindTexture2D() - creates 2D image form buffer.
hipBindTextureToArray() - creates image view.
hipTexRefSetAddress() - creates 1D image from buffer (should create a typed buffer, however this is not compatible with HIP-HCC).
hipTexRefSetAddress2D() - creates 2D image from buffer.
hipTexRefSetArray() - creates image view.
There are still a lot of TODOs in the code, here's a few important ones:
1. VDI doesn't support a lot of sampler flags.
2. VDI doesn't support device to image 2D/3D copy.
3. Mipmaps implementation is incomplete.
4. Image view implementation is incomplete.
Change-Id: Ia374ee27aa14f76451fee7667495036f4419a487
[ROCm/hip commit: c22eb7808d]
The current texture implementation is based off the one for HIP-HCC. There's a lot of problems with it - only creating images from buffers, hard coding logic and ignoring user parameters. This leads to a whole lot of UB even with simple examples (as seen with RedShift's code).
This CL is aimed to bring the HIP-VDI texture implementation closer to what is described by Cuda.
hipMemcpyAtoA() - image to image copy.
hipMemcpyHtoA()/hipMemcpyDtoA() - buffer to image copy.
hipMemcpyAtoH()/hipMemcpyAtoD() - image to buffer copy.
hipArrayCreate()/hipArray3DCreate()/hipMallocArray()/hipMalloc3DArray() - creates 1D/2D/3D/1D Array/2D Array images.
hipCreateTextureObject() - creates sampler, (optional) creates 1D/2D image from buffer, (optional) creates image views.
hipBindTexture() - creates 1D image from buffer (should create a typed buffer, however this is not compatible with HIP-HCC).
hipBindTexture2D() - creates 2D image form buffer.
hipBindTextureToArray() - creates image view.
hipTexRefSetAddress() - creates 1D image from buffer (should create a typed buffer, however this is not compatible with HIP-HCC).
hipTexRefSetAddress2D() - creates 2D image from buffer.
hipTexRefSetArray() - creates image view.
There are still a lot of TODOs in the code, here's a few important ones:
1. VDI doesn't support a lot of sampler flags.
2. VDI doesn't support device to image 2D/3D copy.
3. Mipmaps implementation is incomplete.
4. Image view implementation is incomplete.
Change-Id: Ia374ee27aa14f76451fee7667495036f4419a487
Review comments - generate hiprtc lib everytime when HIP_PLATFORM is hcc
Changes for hip-clang
Removing pre processor directive to simplify
Change-Id: Id38ab368362b58ee0458baeb8051fea709ae6bba
[ROCm/clr commit: 8bf287ef18]
Review comments - generate hiprtc lib everytime when HIP_PLATFORM is hcc
Changes for hip-clang
Removing pre processor directive to simplify
Change-Id: Id38ab368362b58ee0458baeb8051fea709ae6bba
Review comments - generate hiprtc lib everytime when HIP_PLATFORM is hcc
Changes for hip-clang
Removing pre processor directive to simplify
Change-Id: Id38ab368362b58ee0458baeb8051fea709ae6bba
[ROCm/hip commit: 54447268cc]
Review comments - generate hiprtc lib everytime when HIP_PLATFORM is hcc
Changes for hip-clang
Removing pre processor directive to simplify
Change-Id: Id38ab368362b58ee0458baeb8051fea709ae6bba
Checks for an IPC memory error and updates comments relevant
to rocr_visible_devices.
Change-Id: I9d2f2dd27f3fa04881d17387cce2692bc046edb2
[ROCm/ROCR-Runtime commit: a1c2439213]
HDP will now be used for coarse grain kernarg so needs to be
reported without consideration of fine grain vram over pcie.
Change-Id: I648167299faa583876a3d8685c3b3c4d8d31ebf9
HDP will now be used for coarse grain kernarg so needs to be
reported without consideration of fine grain vram over pcie.
Change-Id: I648167299faa583876a3d8685c3b3c4d8d31ebf9
[ROCm/ROCR-Runtime commit: 9c35780836]
Given a process ID, give the device indices that process is
currently using.
Also:
* made corrections to how RSMI, amdgpu (ie, "card#") and
KFD indicies translate from one another
* add a few missing error codes to rsmi_status_string()
* fix some formatting
Change-Id: Icd2cae66bb4fec768da96af7cf9cf8b8b66ec7f9
[ROCm/rocm_smi_lib commit: 2d6e15190c]
Given a process ID, give the device indices that process is
currently using.
Also:
* made corrections to how RSMI, amdgpu (ie, "card#") and
KFD indicies translate from one another
* add a few missing error codes to rsmi_status_string()
* fix some formatting
Change-Id: Icd2cae66bb4fec768da96af7cf9cf8b8b66ec7f9
Given a process ID, give the device indices that process is
currently using.
Also:
* made corrections to how RSMI, amdgpu (ie, "card#") and
KFD indicies translate from one another
* add a few missing error codes to rsmi_status_string()
* fix some formatting
Change-Id: Icd2cae66bb4fec768da96af7cf9cf8b8b66ec7f9
[ROCm/amdsmi commit: 2d6e15190c]
Setting to 1 prevents the scratch handler from reducing peak occupancy.
Scratch allocations that would normally reduce peak occupancy will
instead fail.
Diagnostic for TF and PyTorch.
Change-Id: I2d7ea47077eb5cf708251c8aa3fd183ad4261be0
Setting to 1 prevents the scratch handler from reducing peak occupancy.
Scratch allocations that would normally reduce peak occupancy will
instead fail.
Diagnostic for TF and PyTorch.
Change-Id: I2d7ea47077eb5cf708251c8aa3fd183ad4261be0
[ROCm/ROCR-Runtime commit: dc165c92bc]
scratch_used_large_ was uninitialized leading to the observed hang.
DynamicScratchHandler would wait for a large scratch release despite no
large scratch having yet been allocated. Fixes .
The patch also removes a potential race between AddScratchNotifier and
ReleaseQueueScratch. The race condition does not exist today since both
scratch alloc and release run on the same thread. The changes will
prevent this potential race from manifesting if the async event handler
is ever updated to use multiple threads.
Also enhances scratch occupancy reduction reporting. Reporting now
prints the initial request size as well as the allocated size and the
effect on occupancy this has. Occupancy is computed in terms of the
requesting dispatch grid size so may be >100%.
Change-Id: I0fc5ee01467ff4c29bdd25d545177c97862c3bd9
scratch_used_large_ was uninitialized leading to the observed hang.
DynamicScratchHandler would wait for a large scratch release despite no
large scratch having yet been allocated. Fixes .
The patch also removes a potential race between AddScratchNotifier and
ReleaseQueueScratch. The race condition does not exist today since both
scratch alloc and release run on the same thread. The changes will
prevent this potential race from manifesting if the async event handler
is ever updated to use multiple threads.
Also enhances scratch occupancy reduction reporting. Reporting now
prints the initial request size as well as the allocated size and the
effect on occupancy this has. Occupancy is computed in terms of the
requesting dispatch grid size so may be >100%.
Change-Id: I0fc5ee01467ff4c29bdd25d545177c97862c3bd9
[ROCm/ROCR-Runtime commit: 6c556002d8]
Ensures that all CPU agents will have a pool handle to allocate
system memory. These pools will have no numa binding since the
node their owning Agent represents has no installed memory.
Change-Id: I9f72b455d633646839753c6719ff7f6a4c41f7c4
Ensures that all CPU agents will have a pool handle to allocate
system memory. These pools will have no numa binding since the
node their owning Agent represents has no installed memory.
Change-Id: I9f72b455d633646839753c6719ff7f6a4c41f7c4
[ROCm/ROCR-Runtime commit: d53fe07687]
~45% to 50% of Performance drop on rocBLAS_int8 test
Use the last command in the queue for a wait.
Add extra print information about processed commands.
Add an option to disable file location printing.
Change-Id: I4187883e1a90e571fde3128af98368108fda8785
[ROCm/clr commit: a66d09f5a3]
~45% to 50% of Performance drop on rocBLAS_int8 test
Use the last command in the queue for a wait.
Add extra print information about processed commands.
Add an option to disable file location printing.
Change-Id: I4187883e1a90e571fde3128af98368108fda8785
Vladislav Sytchenko
Payam
jujiang
Jatin Chaudhary
Sean Keely
Chris Freehill
Ramesh Errabolu
German Andryeyev
Chauncey Hui