AI/rocm-systems
2
0 Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
76 333 коммитов 3 Ветки 0 Теги
develop
Граф коммитов
76333 Коммитов
This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
kjayapra-amd b823a939b0 SWDEV-236178 - Fixing func_attributes that was over written on redesign. 
Change-Id: I157913ae4fa4a3a149817e901f10475b7750188b


[ROCm/hip commit: 6f15d8ca6b]
 2020-07-01 11:52:45 -04:00
kjayapra-amd 6f15d8ca6b SWDEV-236178 - Fixing func_attributes that was over written on redesign. 
Change-Id: I157913ae4fa4a3a149817e901f10475b7750188b
 2020-07-01 11:52:45 -04:00
Chauncey Hui 457a9d48f5 SWDEV-2 - Change OpenCL version number from 3169 to 3170 
[ROCm/clr commit: f07fedd00a]
 2020-07-01 03:00:03 -04:00
Chauncey Hui f07fedd00a SWDEV-2 - Change OpenCL version number from 3169 to 3170 2020-07-01 03:00:03 -04:00
Laurent Morichetti 23df617150 Set the correct bit in m0 for gfx10 
The size of the m0 payload for MSG_INTERRUPT has changed in gfx10. It is
now 23bit wide instead of 24bit wide in gfx9.

Since we are generating different binaries for gfx9 and gfx10, we can
conditionally set DEBUG_INTERRUPT_CONTEXT_ID_BIT to 23 for gfx9 and
22 for gfx10.

Change-Id: Ifc15a9fa4399d35328ab58b742f791f1660bcd9a
 2020-06-30 22:02:41 -04:00
Laurent Morichetti ab20abe701 Set the correct bit in m0 for gfx10 
The size of the m0 payload for MSG_INTERRUPT has changed in gfx10. It is
now 23bit wide instead of 24bit wide in gfx9.

Since we are generating different binaries for gfx9 and gfx10, we can
conditionally set DEBUG_INTERRUPT_CONTEXT_ID_BIT to 23 for gfx9 and
22 for gfx10.

Change-Id: Ifc15a9fa4399d35328ab58b742f791f1660bcd9a


[ROCm/ROCR-Runtime commit: 23df617150]
 2020-06-30 22:02:41 -04:00
Chris Freehill 77083980a8 Quiet spurious pthread_unlock warnings 
A message is output in debug builds when pthread_unlock
returns an error. However, in most cases, it should return
EPERM. In fact, if it doesn't return EPERM, it is an
indication of a problem. This commit adjusts accordingly.

Change-Id: Ia5cad89aa6e68e79c1291ea21adffb0fa68f2300


[ROCm/rocm_smi_lib commit: 866438966d]
 2020-06-30 15:12:58 -05:00
Chris Freehill 866438966d Quiet spurious pthread_unlock warnings 
A message is output in debug builds when pthread_unlock
returns an error. However, in most cases, it should return
EPERM. In fact, if it doesn't return EPERM, it is an
indication of a problem. This commit adjusts accordingly.

Change-Id: Ia5cad89aa6e68e79c1291ea21adffb0fa68f2300
 2020-06-30 15:12:58 -05:00
Chris Freehill 5961ce08a9 Quiet spurious pthread_unlock warnings 
A message is output in debug builds when pthread_unlock
returns an error. However, in most cases, it should return
EPERM. In fact, if it doesn't return EPERM, it is an
indication of a problem. This commit adjusts accordingly.

Change-Id: Ia5cad89aa6e68e79c1291ea21adffb0fa68f2300


[ROCm/amdsmi commit: 866438966d]
 2020-06-30 15:12:58 -05:00
Matt Arsenault 4c38d6f0a7 Use option for BUILD_SHARED_LIBS 
This avoids blindly overwriting the setting.

Change-Id: I38dff67f406c4547806a96f4ab220a7415d96242


[ROCm/clr commit: 03ed004255]
 2020-06-30 15:01:46 -04:00
Matt Arsenault 03ed004255 Use option for BUILD_SHARED_LIBS 
This avoids blindly overwriting the setting.

Change-Id: I38dff67f406c4547806a96f4ab220a7415d96242
 2020-06-30 15:01:46 -04:00
Wenkai Du e8da2a0da6 topo_expl: fix broken build (#224) 
[ROCm/rccl commit: a6be82f5ab]
 2020-06-30 11:11:23 -07:00
Wenkai Du a6be82f5ab topo_expl: fix broken build (#224) 2020-06-30 11:11:23 -07:00
Wenkai Du effafd456b Merge pull request #223 from wenkaidu/sendrecv 
Use separate threads for send and receive

[ROCm/rccl commit: a144a85465]
 2020-06-30 10:50:06 -07:00
Wenkai Du a144a85465 Merge pull request #223 from wenkaidu/sendrecv 
Use separate threads for send and receive
 2020-06-30 10:50:06 -07:00
German Andryeyev f2464edb74 Remove hipMemcpyDeviceToDevice check. 
There is hipMemcpyDefault that requires validation also.

Change-Id: I5ae0ffa1c023b7774547acbdc049b84a0c2cb4c5


[ROCm/clr commit: 11b7842f71]
 2020-06-30 12:59:54 -04:00
German Andryeyev 11b7842f71 Remove hipMemcpyDeviceToDevice check. 
There is hipMemcpyDefault that requires validation also.

Change-Id: I5ae0ffa1c023b7774547acbdc049b84a0c2cb4c5
 2020-06-30 12:59:54 -04:00
German Andryeyev 31abf7a6c3 Remove hipMemcpyDeviceToDevice check. 
There is hipMemcpyDefault that requires validation also.

Change-Id: I5ae0ffa1c023b7774547acbdc049b84a0c2cb4c5


[ROCm/hip commit: f2102adc99]
 2020-06-30 12:59:54 -04:00
German Andryeyev f2102adc99 Remove hipMemcpyDeviceToDevice check. 
There is hipMemcpyDefault that requires validation also.

Change-Id: I5ae0ffa1c023b7774547acbdc049b84a0c2cb4c5
 2020-06-30 12:59:54 -04:00
Ronak Chauhan 845c0a5b8a Support passing macros to hipLaunchKernelGGL 
This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.

This is different from 4dfef9a25b.

We try to accomodate the case when a kernel template has multiple
type parameters.

Change-Id: I87577d402c92b0f3b51e298f8293f4065e1f6de8


[ROCm/clr commit: 133251a6e1]
 2020-06-30 10:44:55 -04:00
Ronak Chauhan 133251a6e1 Support passing macros to hipLaunchKernelGGL 
This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.

This is different from fb6bb04f03.

We try to accomodate the case when a kernel template has multiple
type parameters.

Change-Id: I87577d402c92b0f3b51e298f8293f4065e1f6de8
 2020-06-30 10:44:55 -04:00
Ronak Chauhan b1e3842c13 Support passing macros to hipLaunchKernelGGL 
This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.

This is different from b2edee4693.

We try to accomodate the case when a kernel template has multiple
type parameters.

Change-Id: I87577d402c92b0f3b51e298f8293f4065e1f6de8


[ROCm/hip commit: affe9ab9b5]
 2020-06-30 10:44:55 -04:00
Ronak Chauhan affe9ab9b5 Support passing macros to hipLaunchKernelGGL 
This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.

This is different from 961717879d.

We try to accomodate the case when a kernel template has multiple
type parameters.

Change-Id: I87577d402c92b0f3b51e298f8293f4065e1f6de8
 2020-06-30 10:44:55 -04:00
Cole Nelson 141246eeeb libhsakmt: set packaging arch, field separators, vendor info 
Change-Id: Ia1392285f5ee0beeaae136ad7d68e1723bc590ba
Signed-off-by: Cole Nelson <cole.nelson@amd.com>
 2020-06-30 07:38:14 -04:00
Cole Nelson 86b8707391 libhsakmt: set packaging arch, field separators, vendor info 
Change-Id: Ia1392285f5ee0beeaae136ad7d68e1723bc590ba
Signed-off-by: Cole Nelson <cole.nelson@amd.com>


[ROCm/ROCR-Runtime commit: 141246eeeb]
 2020-06-30 07:38:14 -04:00
Jason Tang c0a9560c1b Fix CentOS build 
Change-Id: Id0956f2a876077a3528c4fafc136586b95fdda70


[ROCm/clr commit: 0394f79d4d]
 2020-06-29 18:49:48 -04:00
Jason Tang 0394f79d4d Fix CentOS build 
Change-Id: Id0956f2a876077a3528c4fafc136586b95fdda70
 2020-06-29 18:49:48 -04:00
Payam 228d8e7c12 update debug print time to be us 
Change-Id: I6f49304414ffc209f0fa1cb7199557c8423fcfa7


[ROCm/clr commit: 07848d7926]
 2020-06-29 18:45:24 -04:00
Payam 07848d7926 update debug print time to be us 
Change-Id: I6f49304414ffc209f0fa1cb7199557c8423fcfa7
 2020-06-29 18:45:24 -04:00
Divya Shikre 33f4141218 OAM: Implement get_sensors_info() 
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ia2c6e18f463c0f97530ca8ad07d249e6f2116534


[ROCm/rocm_smi_lib commit: e21232f059]
 2020-06-29 14:50:19 -04:00
Divya Shikre e21232f059 OAM: Implement get_sensors_info() 
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ia2c6e18f463c0f97530ca8ad07d249e6f2116534
 2020-06-29 14:50:19 -04:00
Divya Shikre 05c7aa953f OAM: Implement get_sensors_info() 
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ia2c6e18f463c0f97530ca8ad07d249e6f2116534


[ROCm/amdsmi commit: e21232f059]
 2020-06-29 14:50:19 -04:00
Evgeny f6e42f2614 mem_manager.py packaging fix 
Change-Id: I8faf85056f97e8bcbc4b3511d351b9974c3c9d75
 2020-06-29 13:27:22 -05:00
Evgeny 4187f10eb3 mem_manager.py packaging fix 
Change-Id: I8faf85056f97e8bcbc4b3511d351b9974c3c9d75


[ROCm/rocprofiler commit: f6e42f2614]
 2020-06-29 13:27:22 -05:00
Daniil Fukalov a2e2f9b8c6 Add __attribute__((const)) to grid related functions declarations 
This is cherrypick of Daniil Fukalov's PR https://github.com/ROCm-Developer-Tools/HIP/pull/2110
which has been committed to master branch.

Make declarations consistent with https://github.com/RadeonOpenCompute/ROCm-Device-Libs/blob/amd-stg-open/ockl/src/workitem.cl
Without the attribute these functions don't have "readnone" LLVM IR attribute. Without it some optimizations fails, e.g. Loop Invariant Code Motion doesn't hoist these calls out of a loop.

Change-Id: Idb599570d142152cc4f6a3c8986384ad7f0c4729


[ROCm/clr commit: 359ea4fcaf]
 2020-06-29 13:33:18 -04:00
Daniil Fukalov 359ea4fcaf Add __attribute__((const)) to grid related functions declarations 
This is cherrypick of Daniil Fukalov's PR https://github.com/ROCm-Developer-Tools/HIP/pull/2110
which has been committed to master branch.

Make declarations consistent with https://github.com/RadeonOpenCompute/ROCm-Device-Libs/blob/amd-stg-open/ockl/src/workitem.cl
Without the attribute these functions don't have "readnone" LLVM IR attribute. Without it some optimizations fails, e.g. Loop Invariant Code Motion doesn't hoist these calls out of a loop.

Change-Id: Idb599570d142152cc4f6a3c8986384ad7f0c4729
 2020-06-29 13:33:18 -04:00
Daniil Fukalov fd5e6254ab Add __attribute__((const)) to grid related functions declarations 
This is cherrypick of Daniil Fukalov's PR https://github.com/ROCm-Developer-Tools/HIP/pull/2110
which has been committed to master branch.

Make declarations consistent with https://github.com/RadeonOpenCompute/ROCm-Device-Libs/blob/amd-stg-open/ockl/src/workitem.cl
Without the attribute these functions don't have "readnone" LLVM IR attribute. Without it some optimizations fails, e.g. Loop Invariant Code Motion doesn't hoist these calls out of a loop.

Change-Id: Idb599570d142152cc4f6a3c8986384ad7f0c4729


[ROCm/hip commit: 63e44d16a3]
 2020-06-29 13:33:18 -04:00
Daniil Fukalov 63e44d16a3 Add __attribute__((const)) to grid related functions declarations 
This is cherrypick of Daniil Fukalov's PR https://github.com/ROCm-Developer-Tools/HIP/pull/2110
which has been committed to master branch.

Make declarations consistent with https://github.com/RadeonOpenCompute/ROCm-Device-Libs/blob/amd-stg-open/ockl/src/workitem.cl
Without the attribute these functions don't have "readnone" LLVM IR attribute. Without it some optimizations fails, e.g. Loop Invariant Code Motion doesn't hoist these calls out of a loop.

Change-Id: Idb599570d142152cc4f6a3c8986384ad7f0c4729
 2020-06-29 13:33:18 -04:00
Wenkai Du ac87c9db37 gtest: extend testing up to 8 GPUs 
[ROCm/rccl commit: 8db0aa8f4c]
 2020-06-29 09:32:31 -07:00
Wenkai Du 8db0aa8f4c gtest: extend testing up to 8 GPUs 2020-06-29 09:32:31 -07:00
Wenkai Du 77d94493c3 Merge sendrecv kernel from NCCL 2.7.3 
This commit was cherry-picked and modified from
https://github.com/NVIDIA/nccl/commit/89072c82e551d7c8bf7bd5ca77780ef540b7611e


[ROCm/rccl commit: 964c4c2061]
 2020-06-29 08:47:46 -07:00
Wenkai Du 964c4c2061 Merge sendrecv kernel from NCCL 2.7.3 
This commit was cherry-picked and modified from
https://github.com/NVIDIA/nccl/commit/5949d96f36d050e59d05872f8bbffd2549318e95
 2020-06-29 08:47:46 -07:00
Wenkai Du 3c674c9c1f Use separate threads for send and receive 
[ROCm/rccl commit: b90735c935]
 2020-06-29 08:47:15 -07:00
Wenkai Du b90735c935 Use separate threads for send and receive 2020-06-29 08:47:15 -07:00
Gang Ba fec3780c1a Revert "libhsakmt: add Streaming Performance Monitors APIs" 
This reverts commit d675d1cce1.

Reason for revert: Change was submitted by accident

Change-Id: If05c705e22296fd3ca789f269737d379a933361d
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
 2020-06-29 10:54:54 -04:00
Gang Ba 04e57413f4 Revert "libhsakmt: add Streaming Performance Monitors APIs" 
This reverts commit c0a0ada18b.

Reason for revert: Change was submitted by accident

Change-Id: If05c705e22296fd3ca789f269737d379a933361d
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>


[ROCm/ROCR-Runtime commit: fec3780c1a]
 2020-06-29 10:54:54 -04:00
Evgeny c196fbe0d5 JSON trace dependencies flow to-tid fix 
Change-Id: If21b12d0560e7db07b1ff02e0441addff3453cbe
 2020-06-29 01:16:05 -05:00
Evgeny 1a84fa2528 JSON trace dependencies flow to-tid fix 
Change-Id: If21b12d0560e7db07b1ff02e0441addff3453cbe


[ROCm/rocprofiler commit: c196fbe0d5]
 2020-06-29 01:16:05 -05:00
Jason Tang 3c0b0d9d92 Not to use fixnames 
Change-Id: I50c9503cad1fc072edec989a4f82a27bb7bb3909


[ROCm/clr commit: 4666113db0]
 2020-06-28 18:57:16 -04:00
Jason Tang 4666113db0 Not to use fixnames 
Change-Id: I50c9503cad1fc072edec989a4f82a27bb7bb3909
 2020-06-28 18:57:16 -04:00