AI/rocm-systems
2
0
Derivar 0
Código Questões Pedidos de integração Operações Pacotes Planeamentos Lançamentos Wiki Trabalho
76 333 Cometimentos 3 Ramos 0 Etiquetas
develop
Gráfico de cometimentos

76333 Cometimentos

Este ramo
Este ramo
Todos os ramos
Autor(a) SHA1 Mensagem Data
colramos-amd 8540fde54a Move error logging to util.py 
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: b99d448d3b]
 2023-12-11 16:49:06 -06:00
colramos-amd b99d448d3b Move error logging to util.py 
Signed-off-by: colramos-amd <colramos@amd.com>
 2023-12-11 16:49:06 -06:00
Karl W Schulz d4d22af34a fix comment typo 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: eaae69e2a6]
 2023-12-11 16:49:06 -06:00
Karl W Schulz eaae69e2a6 fix comment typo 
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
 2023-12-11 16:49:06 -06:00
colramos-amd 42b6336cb5 Initial overhaul of Analyze mode. Basic CLI is enabled. 
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 57a63b6eb1]
 2023-12-11 16:49:06 -06:00
colramos-amd 57a63b6eb1 Initial overhaul of Analyze mode. Basic CLI is enabled. 
Signed-off-by: colramos-amd <colramos@amd.com>
 2023-12-11 16:49:06 -06:00
Aryan Salmanpour 5a9f519761 Don't call DestroyDataBuffers during the reconfiguration - this function will be called during SubmitDecode (#131) 
[ROCm/rocdecode commit: b8a8b66b91]
 2023-12-11 17:10:10 -05:00
Aryan Salmanpour b8a8b66b91 Don't call DestroyDataBuffers during the reconfiguration - this function will be called during SubmitDecode (#131) 2023-12-11 17:10:10 -05:00
Aryan Salmanpour b62bf4a6a1 Fix perf drop on some MI250 nodes - create VABuffers for every submission, and don't use vaMapBuffer/vaUnmapBuffer (#129) 
* create VABuffers for every submission, and don't use vaMapBuffer/vaUnmapBuffer

* code clean up

* address review comments

[ROCm/rocdecode commit: b77d00e38e]
 2023-12-11 15:40:50 -05:00
Aryan Salmanpour b77d00e38e Fix perf drop on some MI250 nodes - create VABuffers for every submission, and don't use vaMapBuffer/vaUnmapBuffer (#129) 
* create VABuffers for every submission, and don't use vaMapBuffer/vaUnmapBuffer

* code clean up

* address review comments
 2023-12-11 15:40:50 -05:00
Benjamin Welton cad071f395 Added kernel id to enqueue callback for kernel dispatch (#276) 
Adds kernel id as parameter to rocprofiler_profile_counting_dispatch_callback_t.
Small cleanup of code in core.cpp.

[ROCm/rocprofiler-sdk commit: d2a6eec1bf]
 2023-12-11 09:13:48 -08:00
Benjamin Welton d2a6eec1bf Added kernel id to enqueue callback for kernel dispatch (#276) 
Adds kernel id as parameter to rocprofiler_profile_counting_dispatch_callback_t.
Small cleanup of code in core.cpp.
 2023-12-11 09:13:48 -08:00
Bertan Dogancay fe5a902f97 correct package name (#1012) 
[ROCm/rccl commit: fca459baaf]
 2023-12-11 09:40:29 -07:00
Bertan Dogancay fca459baaf correct package name (#1012) 2023-12-11 09:40:29 -07:00
Alex Xie 5aaa498e45 SWDEV-434373 - Add icd config to opencl package 
Change-Id: Id2d143ae82b0fa4d5321912fca9daa1e958f1fb6


[ROCm/clr commit: 5a3c4ea49d]
 2023-12-11 11:17:37 -05:00
Alex Xie 5a3c4ea49d SWDEV-434373 - Add icd config to opencl package 
Change-Id: Id2d143ae82b0fa4d5321912fca9daa1e958f1fb6
 2023-12-11 11:17:37 -05:00
vlaindic 8d80b2969d SWDEV-428255: CTF plugin shows hipDeviceReset 
rocprofv2's CTF plugin is adapted to show hipDeviceReset in the
HIP API trace. Credits to Philippe Proulx <pproulx@efficios.com>

Change-Id: I870458758402e76f736007f8f2ca807059a02559
 2023-12-11 08:56:10 +01:00
vlaindic 96510269a5 SWDEV-428255: CTF plugin shows hipDeviceReset 
rocprofv2's CTF plugin is adapted to show hipDeviceReset in the
HIP API trace. Credits to Philippe Proulx <pproulx@efficios.com>

Change-Id: I870458758402e76f736007f8f2ca807059a02559


[ROCm/rocprofiler commit: 8d80b2969d]
 2023-12-11 08:56:10 +01:00
Wenkai Du 481a35bc59 Fix memory fence and use non-temporal store (#1007) 
* Fix memory fence and use non-temporal store

* Use amdgcn builtin instead of inline asm

* Move threadfence location

* Revert changes to gfx90a

* Rework gfx90a change

* Apply changes to gfx94x

[ROCm/rccl commit: 7965c8b53c]
 2023-12-09 12:16:08 -08:00
Wenkai Du 7965c8b53c Fix memory fence and use non-temporal store (#1007) 
* Fix memory fence and use non-temporal store

* Use amdgcn builtin instead of inline asm

* Move threadfence location

* Revert changes to gfx90a

* Rework gfx90a change

* Apply changes to gfx94x
 2023-12-09 12:16:08 -08:00
Ziyue Yang fe250212bf Fix MSCCL scratch allocation (#1010) 
[ROCm/rccl commit: c002f20029]
 2023-12-08 17:47:10 -06:00
Ziyue Yang c002f20029 Fix MSCCL scratch allocation (#1010) 2023-12-08 17:47:10 -06:00
Ziyue Yang 62299668bd Tune MSCCL all-reduce algorithm (#1009) 
[ROCm/rccl commit: bb144dcd50]
 2023-12-08 17:47:02 -06:00
Ziyue Yang bb144dcd50 Tune MSCCL all-reduce algorithm (#1009) 2023-12-08 17:47:02 -06:00
Wen-Heng (Jack) Chung 529f72ceaa Relax workgroup barrier implementation for MSCCL send/recv ops. (#997) 
* Trim logic.

* Revert "Trim logic."

This reverts commit 8f2dba6c764108acf2bf5428366b9f41d4d206b9.

* Introduce MSCCL template parameters to send / recv.

* Address review feedbacks.

[ROCm/rccl commit: baadda4bd8]
 2023-12-08 17:46:53 -06:00
Wen-Heng (Jack) Chung baadda4bd8 Relax workgroup barrier implementation for MSCCL send/recv ops. (#997) 
* Trim logic.

* Revert "Trim logic."

This reverts commit 8f2dba6c764108acf2bf5428366b9f41d4d206b9.

* Introduce MSCCL template parameters to send / recv.

* Address review feedbacks.
 2023-12-08 17:46:53 -06:00
jeffqjiangNew a265b9a3da * rocDecode: Fix for the performance regression introduced by PR#114. (#128) 
- Skip the additional buffer bumping specified in process C.5.2.2., to avoid synchronous job submission in some cases.
  - Increase DPB buffer size now by 2 to avoid overwriting pictures to be output.

[ROCm/rocdecode commit: a2dfa8bc26]
 2023-12-08 17:53:01 -05:00
jeffqjiangNew a2dfa8bc26 * rocDecode: Fix for the performance regression introduced by PR#114. (#128) 
- Skip the additional buffer bumping specified in process C.5.2.2., to avoid synchronous job submission in some cases.
  - Increase DPB buffer size now by 2 to avoid overwriting pictures to be output.
 2023-12-08 17:53:01 -05:00
Rajy Rawther e651268fab added release of copied buffers in host and hip (#126) 
* added release of copied buffers in host and hip

* address review comments

* addressed review comment

[ROCm/rocdecode commit: 1dc5a9d798]
 2023-12-08 17:29:00 -05:00
Rajy Rawther 1dc5a9d798 added release of copied buffers in host and hip (#126) 
* added release of copied buffers in host and hip

* address review comments

* addressed review comment
 2023-12-08 17:29:00 -05:00
Sam Wu 5890852ff1 Standardize documentation for ReadtheDocs 
Relates to https://github.com/RadeonOpenCompute/rocm-docs-core/issues/330

Change-Id: Ic9370548bb8d919376b20f7e1800fe620369e69b
 2023-12-08 16:56:59 -05:00
Sam Wu a9ad3af5e2 Standardize documentation for ReadtheDocs 
Relates to https://github.com/RadeonOpenCompute/rocm-docs-core/issues/330

Change-Id: Ic9370548bb8d919376b20f7e1800fe620369e69b


[ROCm/rdc commit: 5890852ff1]
 2023-12-08 16:56:59 -05:00
German fe71f14732 SWDEV-434241 - Replace size_t with uint64_t 
The kernel accepts uint64_t, but with 32bit OCL build size_t was 32 bit

Change-Id: I6fe37d2e5e69c7bd62d7b1bd4cace758758b3482


[ROCm/clr commit: b3171d08e6]
 2023-12-08 16:56:29 -05:00
German b3171d08e6 SWDEV-434241 - Replace size_t with uint64_t 
The kernel accepts uint64_t, but with 32bit OCL build size_t was 32 bit

Change-Id: I6fe37d2e5e69c7bd62d7b1bd4cace758758b3482
 2023-12-08 16:56:29 -05:00
gaba 4bf73f521b libhsakmt: Fix CPU cache issue 
For "Intel Meteor lake Mobile", the cache info is not in sysfs,
    That means /sys/devices/system/node/node%d/%s/cache is not exist,
    but system working fine.

Change-Id: Ie7c04426791a84c2288ff21df093226828a5f629
Signed-off-by: Gang Ba <Gang.Ba@amd.com>
 2023-12-08 15:29:19 -05:00
gaba dcf8b5fd6c libhsakmt: Fix CPU cache issue 
For "Intel Meteor lake Mobile", the cache info is not in sysfs,
    That means /sys/devices/system/node/node%d/%s/cache is not exist,
    but system working fine.

Change-Id: Ie7c04426791a84c2288ff21df093226828a5f629
Signed-off-by: Gang Ba <Gang.Ba@amd.com>


[ROCm/ROCR-Runtime commit: 4bf73f521b]
 2023-12-08 15:29:19 -05:00
Todd tiantuo Li c7abb07c97 SWDEV-422544 - Use hipDeviceAttributeUnifiedAddressing as APU flag 
Change-Id: If718a20f62f0ba8d83c01a0b2d16ff3f706f7bd4


[ROCm/clr commit: b825decd42]
 2023-12-08 11:40:34 -05:00
Todd tiantuo Li b825decd42 SWDEV-422544 - Use hipDeviceAttributeUnifiedAddressing as APU flag 
Change-Id: If718a20f62f0ba8d83c01a0b2d16ff3f706f7bd4
 2023-12-08 11:40:34 -05:00
Vladimir Indic 2271ed7730 pcs parser: includes fixed, GLOB removed (#286) 
* pcs parser: includes fixed, GLOB removed

* source formatting (clang-format v11) (#287)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* cmake formatting (cmake-format) (#288)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

[ROCm/rocprofiler-sdk commit: 200be03bb4]
 2023-12-08 17:36:32 +01:00
Vladimir Indic 200be03bb4 pcs parser: includes fixed, GLOB removed (#286) 
* pcs parser: includes fixed, GLOB removed

* source formatting (clang-format v11) (#287)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

* cmake formatting (cmake-format) (#288)

Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: vlaindic <vlaindic@users.noreply.github.com>
 2023-12-08 17:36:32 +01:00
Satyanvesh Dittakavi a374f74baa SWDEV-432684 - SWDEV-433437 - Fix test_gpu_jit MIGraphx test failure 
Add clang pragma push and pop diagnostics for ignoring "-Weverything"
in the hiprtc builtins header. Otherwise this will ignore even the
geniune errors occurring in the hiprtc kernels.

Change-Id: I8c3dacf902732b2ea495d83e797369f8aebd75d6


[ROCm/clr commit: 912cc407a4]
 2023-12-08 11:12:43 -05:00
Satyanvesh Dittakavi 912cc407a4 SWDEV-432684 - SWDEV-433437 - Fix test_gpu_jit MIGraphx test failure 
Add clang pragma push and pop diagnostics for ignoring "-Weverything"
in the hiprtc builtins header. Otherwise this will ignore even the
geniune errors occurring in the hiprtc kernels.

Change-Id: I8c3dacf902732b2ea495d83e797369f8aebd75d6
 2023-12-08 11:12:43 -05:00
Jaydeep Patel a44c628719 SWDEV-429009 - Moved hipDeviceAttributeHostRegisterSupported in end as having inbetween breaks compatibility with blender (No GPU Detected issue). 
Change-Id: I3f83a2813d917448bddae2a9cb2ba67d8b8ce0b0


[ROCm/hip commit: 6cb746858d]
 2023-12-08 11:02:27 -05:00
Jaydeep Patel 6cb746858d SWDEV-429009 - Moved hipDeviceAttributeHostRegisterSupported in end as having inbetween breaks compatibility with blender (No GPU Detected issue). 
Change-Id: I3f83a2813d917448bddae2a9cb2ba67d8b8ce0b0
 2023-12-08 11:02:27 -05:00
Nives Vukovic 8c4b2675cc EXSWHTEC-173 - Implement tests for Graph Node dependencies APIs (#50) 
Recreation of github PR https://github.com/ROCm-Developer-Tools/hip-tests/pull/50

Change-Id: I65707d9d0bfa12c08d82779c1402215f22d7815b


[ROCm/hip-tests commit: 91ee1399df]
 2023-12-08 10:28:47 -05:00
Nives Vukovic 91ee1399df EXSWHTEC-173 - Implement tests for Graph Node dependencies APIs (#50) 
Recreation of github PR https://github.com/ROCm-Developer-Tools/hip-tests/pull/50

Change-Id: I65707d9d0bfa12c08d82779c1402215f22d7815b
 2023-12-08 10:28:47 -05:00
Jatin Chaudhary 3057d60aec SWDEV-429802 - add address sanitizer build option to hip-tests 
Change-Id: I5662e1d7a08c81239e043ddc7b48853a414a3556


[ROCm/hip-tests commit: 7cfc4a3664]
 2023-12-08 10:25:29 -05:00
Jatin Chaudhary 7cfc4a3664 SWDEV-429802 - add address sanitizer build option to hip-tests 
Change-Id: I5662e1d7a08c81239e043ddc7b48853a414a3556
 2023-12-08 10:25:29 -05:00
Jaydeep Patel 2c41a3c2f4 SWDEV-411680 - Create stream after device is set. 
Change-Id: I3eec0b6855ff9377fdd5bc34128cac9e4af9ec7f


[ROCm/hip-tests commit: cd6796db58]
 2023-12-08 10:23:46 -05:00
Jaydeep Patel cd6796db58 SWDEV-411680 - Create stream after device is set. 
Change-Id: I3eec0b6855ff9377fdd5bc34128cac9e4af9ec7f
 2023-12-08 10:23:46 -05:00