76333 Commit
Autore SHA1 Messaggio Data
Sameer Sahasrabuddhe f0a9c129a0 Implement assert() using the new fprintf_stderr facility
The device library now provides functions to specify the host stderr
stream in a hostcall printf message. This change implements an
assert() macro which can construct such a message. The end result is
that assertions on the device are now correctly printed on the host
stderr instead of stdout.

Change-Id: I85ab8f7848bcf28303cb8dbb8a798bc6aece7d75


[ROCm/hip commit: 96be8a7b73]
2021-01-17 23:54:46 -05:00
Sameer Sahasrabuddhe 96be8a7b73 Implement assert() using the new fprintf_stderr facility
The device library now provides functions to specify the host stderr
stream in a hostcall printf message. This change implements an
assert() macro which can construct such a message. The end result is
that assertions on the device are now correctly printed on the host
stderr instead of stdout.

Change-Id: I85ab8f7848bcf28303cb8dbb8a798bc6aece7d75
2021-01-17 23:54:46 -05:00
Wenkai Du 7f9c15b843 Use less unroll for clique kernels (#313)
[ROCm/rccl commit: 41e47a36e7]
2021-01-15 17:48:10 -08:00
Wenkai Du 41e47a36e7 Use less unroll for clique kernels (#313) 2021-01-15 17:48:10 -08:00
Stanley Tsang d7ed44eb9a Adding multiprocess unit tests (#312)
Adding multiprocess unit tests for collectives.  

To run, NCCL_COMM_ID=$HOSTNAME:12345 build/release/test/UnitTestsMultiProcess

[ROCm/rccl commit: d3fa257682]
2021-01-15 16:34:36 -07:00
Stanley Tsang d3fa257682 Adding multiprocess unit tests (#312)
Adding multiprocess unit tests for collectives.  

To run, NCCL_COMM_ID=$HOSTNAME:12345 build/release/test/UnitTestsMultiProcess
2021-01-15 16:34:36 -07:00
Chris Freehill 09bc75bf0d Correct some target ID strings for gfx908
Change-Id: I7833b561447b9928447cf49472cfe1ca1867e71d
2021-01-15 14:56:38 -06:00
Chris Freehill 33438e7adc Correct some target ID strings for gfx908
Change-Id: I7833b561447b9928447cf49472cfe1ca1867e71d


[ROCm/ROCR-Runtime commit: 09bc75bf0d]
2021-01-15 14:56:38 -06:00
Kent Russell b15eab2821 CMakeLIsts: Fix libasan usage
static-libasan doesn't exist, so use the easier-to-remember
shared-libsan and change static-libasan to static-libsan

Signed-off-by: Kent Russell <kent.russell@amd.com>
Change-Id: Ieef480aacdd770f3bb40673a2e8f8306b308b1c9


[ROCm/rocm_smi_lib commit: ef7f99a7e2]
2021-01-15 15:39:05 -05:00
Kent Russell ef7f99a7e2 CMakeLIsts: Fix libasan usage
static-libasan doesn't exist, so use the easier-to-remember
shared-libsan and change static-libasan to static-libsan

Signed-off-by: Kent Russell <kent.russell@amd.com>
Change-Id: Ieef480aacdd770f3bb40673a2e8f8306b308b1c9
2021-01-15 15:39:05 -05:00
Kent Russell 4a35269cc1 CMakeLIsts: Fix libasan usage
static-libasan doesn't exist, so use the easier-to-remember
shared-libsan and change static-libasan to static-libsan

Signed-off-by: Kent Russell <kent.russell@amd.com>
Change-Id: Ieef480aacdd770f3bb40673a2e8f8306b308b1c9


[ROCm/amdsmi commit: ef7f99a7e2]
2021-01-15 15:39:05 -05:00
David Salinas b6ac0c8655 remove extractkernel
Change-Id: I46a380059fa336aa7553669629a21e8aa7717e7b


[ROCm/clr commit: de3031988d]
2021-01-15 11:34:32 -08:00
David Salinas de3031988d remove extractkernel
Change-Id: I46a380059fa336aa7553669629a21e8aa7717e7b
2021-01-15 11:34:32 -08:00
David Salinas 7f580a29b0 remove extractkernel
Change-Id: I46a380059fa336aa7553669629a21e8aa7717e7b


[ROCm/hip commit: 5f96929cf6]
2021-01-15 11:34:32 -08:00
David Salinas 5f96929cf6 remove extractkernel
Change-Id: I46a380059fa336aa7553669629a21e8aa7717e7b
2021-01-15 11:34:32 -08:00
Satyanvesh Dittakavi 7b8972f41e device property __HIP_ARCH_HAS_SHARED_INT64_ATOMICS__ set to 1 as it has compiler support
Change-Id: Ic91c4955d4f2d52d844471f81e6f0d19418018f5


[ROCm/clr commit: 84cda7f9c2]
2021-01-15 11:40:09 -05:00
Satyanvesh Dittakavi 84cda7f9c2 device property __HIP_ARCH_HAS_SHARED_INT64_ATOMICS__ set to 1 as it has compiler support
Change-Id: Ic91c4955d4f2d52d844471f81e6f0d19418018f5
2021-01-15 11:40:09 -05:00
Satyanvesh Dittakavi 5c60465932 device property __HIP_ARCH_HAS_SHARED_INT64_ATOMICS__ set to 1 as it has compiler support
Change-Id: Ic91c4955d4f2d52d844471f81e6f0d19418018f5


[ROCm/hip commit: aaa15a7455]
2021-01-15 11:40:09 -05:00
Satyanvesh Dittakavi aaa15a7455 device property __HIP_ARCH_HAS_SHARED_INT64_ATOMICS__ set to 1 as it has compiler support
Change-Id: Ic91c4955d4f2d52d844471f81e6f0d19418018f5
2021-01-15 11:40:09 -05:00
Chauncey Hui d4457a2a8a SWDEV-2 - Change OpenCL version number from 3243 to 3244
[ROCm/clr commit: 97dd6c128b]
2021-01-15 03:00:06 -05:00
Chauncey Hui 97dd6c128b SWDEV-2 - Change OpenCL version number from 3243 to 3244 2021-01-15 03:00:06 -05:00
DURGESH KROTTAPALLI 80f1fdb5b7 [dtest] Kernel Execution time fix for hipExtLaunchKernelGGL and hipExtModuleLaunchKernel API's
Fix for kernel execution time using clock rate

SWDEV-238517 for enhancing hip unit tests

Change-Id: Id06df31387ecab96f219e0c1fbcdda1609f75605


[ROCm/clr commit: d27db0f038]
2021-01-15 01:58:22 -05:00
DURGESH KROTTAPALLI d27db0f038 [dtest] Kernel Execution time fix for hipExtLaunchKernelGGL and hipExtModuleLaunchKernel API's
Fix for kernel execution time using clock rate

SWDEV-238517 for enhancing hip unit tests

Change-Id: Id06df31387ecab96f219e0c1fbcdda1609f75605
2021-01-15 01:58:22 -05:00
DURGESH KROTTAPALLI 76eb4b7b1e [dtest] Kernel Execution time fix for hipExtLaunchKernelGGL and hipExtModuleLaunchKernel API's
Fix for kernel execution time using clock rate

SWDEV-238517 for enhancing hip unit tests

Change-Id: Id06df31387ecab96f219e0c1fbcdda1609f75605


[ROCm/hip commit: 0b871a24f6]
2021-01-15 01:58:22 -05:00
DURGESH KROTTAPALLI 0b871a24f6 [dtest] Kernel Execution time fix for hipExtLaunchKernelGGL and hipExtModuleLaunchKernel API's
Fix for kernel execution time using clock rate

SWDEV-238517 for enhancing hip unit tests

Change-Id: Id06df31387ecab96f219e0c1fbcdda1609f75605
2021-01-15 01:58:22 -05:00
Prike.Liang 7e184ebb3a libhsakmt: add more gfx90c family device support
This patch is to add Cezanne/Lucienne support on thunk.

Change-Id: Icd9b9913fa87bbfe6c71b36a2892d6ddb73e3ddd
Signed-off-by: Prike.Liang <Prike.Liang@amd.com>
2021-01-15 09:48:41 +08:00
Prike.Liang a991dda23b libhsakmt: add more gfx90c family device support
This patch is to add Cezanne/Lucienne support on thunk.

Change-Id: Icd9b9913fa87bbfe6c71b36a2892d6ddb73e3ddd
Signed-off-by: Prike.Liang <Prike.Liang@amd.com>


[ROCm/ROCR-Runtime commit: 7e184ebb3a]
2021-01-15 09:48:41 +08:00
Wenkai Du d4382de267 Improve collective trace
[ROCm/rccl commit: 2ddbe6646b]
2021-01-14 19:28:01 -05:00
Wenkai Du 2ddbe6646b Improve collective trace 2021-01-14 19:28:01 -05:00
Wenkai Du 560224fe9f gtest: add scatter to combined calls and use loops (#303)
* gtest: add scatter to combined calls and use loops

* gtest: run validation inside loop

* gtest: revert small element count to 2520

* gtest: fix memory leak in validation

(cherry picked from commit 36935cfbee)

* Fix combined call UT

* Fix memory leak

* Fix alltoallv test


[ROCm/rccl commit: b33a2cac8b]
2021-01-14 19:28:01 -05:00
Wenkai Du b33a2cac8b gtest: add scatter to combined calls and use loops (#303)
* gtest: add scatter to combined calls and use loops

* gtest: run validation inside loop

* gtest: revert small element count to 2520

* gtest: fix memory leak in validation

(cherry picked from commit b0853ccd51)

* Fix combined call UT

* Fix memory leak

* Fix alltoallv test
2021-01-14 19:28:01 -05:00
Wenkai Du 2c49121171 Port alltoall[v]
[ROCm/rccl commit: f4d5d3d620]
2021-01-14 19:28:01 -05:00
Wenkai Du f4d5d3d620 Port alltoall[v] 2021-01-14 19:28:01 -05:00
Wenkai Du 41bead5a4e Do not allow GPU as intermediate
[ROCm/rccl commit: 105db19a11]
2021-01-14 19:28:01 -05:00
Wenkai Du 105db19a11 Do not allow GPU as intermediate 2021-01-14 19:28:01 -05:00
Wenkai Du 34c6013299 Revert "Changes to topology based on XGMI (#272)"
This reverts commit 0a9adc16f4.


[ROCm/rccl commit: e055229e56]
2021-01-14 19:28:01 -05:00
Wenkai Du e055229e56 Revert "Changes to topology based on XGMI (#272)"
This reverts commit 01bd2573db.
2021-01-14 19:28:01 -05:00
Wenkai Du adff98765c Merge remote-tracking branch 'nccl/master' into no-target-id
[ROCm/rccl commit: d469947641]
2021-01-14 19:27:53 -05:00
Wenkai Du d469947641 Merge remote-tracking branch 'nccl/master' into no-target-id 2021-01-14 19:27:53 -05:00
David Salinas 5eb35595fb add new code object tooling: roc-obj-ls and roc-obj-extract
SWDEV-229776

Change-Id: Icb11c4552515d3eff3bcf303c4a470ab90d1dd58


[ROCm/clr commit: 7e9b9534d3]
2021-01-14 14:45:46 -05:00
David Salinas 7e9b9534d3 add new code object tooling: roc-obj-ls and roc-obj-extract
SWDEV-229776

Change-Id: Icb11c4552515d3eff3bcf303c4a470ab90d1dd58
2021-01-14 14:45:46 -05:00
David Salinas e7073fc17c add new code object tooling: roc-obj-ls and roc-obj-extract
SWDEV-229776

Change-Id: Icb11c4552515d3eff3bcf303c4a470ab90d1dd58


[ROCm/hip commit: cb859b7263]
2021-01-14 14:45:46 -05:00
David Salinas cb859b7263 add new code object tooling: roc-obj-ls and roc-obj-extract
SWDEV-229776

Change-Id: Icb11c4552515d3eff3bcf303c4a470ab90d1dd58
2021-01-14 14:45:46 -05:00
Tao Sang 52954de0eb Fix building mathlibs failure
Add back
__HIP_PLATFORM_HCC__
__HIP_PLATFORM_NVCC__

Change-Id: I1ae48678eafd849d6c25bcb204c1724b026be22f


[ROCm/clr commit: 8fc1ff7d4f]
2021-01-14 14:03:15 -05:00
Tao Sang 8fc1ff7d4f Fix building mathlibs failure
Add back
__HIP_PLATFORM_HCC__
__HIP_PLATFORM_NVCC__

Change-Id: I1ae48678eafd849d6c25bcb204c1724b026be22f
2021-01-14 14:03:15 -05:00
Tao Sang 118c6ba23e Fix building mathlibs failure
Add back
__HIP_PLATFORM_HCC__
__HIP_PLATFORM_NVCC__

Change-Id: I1ae48678eafd849d6c25bcb204c1724b026be22f


[ROCm/hip commit: 59ef7dc9e2]
2021-01-14 14:03:15 -05:00
Tao Sang 59ef7dc9e2 Fix building mathlibs failure
Add back
__HIP_PLATFORM_HCC__
__HIP_PLATFORM_NVCC__

Change-Id: I1ae48678eafd849d6c25bcb204c1724b026be22f
2021-01-14 14:03:15 -05:00
Saleel Kudchadker fff9c7f413 Cleanup redundant Barrier packet fill function
Change-Id: I31f3250f00a362c2fdd35aca31df177fed7ddb98


[ROCm/clr commit: ce56d04dee]
2021-01-14 12:38:00 -05:00
Saleel Kudchadker ce56d04dee Cleanup redundant Barrier packet fill function
Change-Id: I31f3250f00a362c2fdd35aca31df177fed7ddb98
2021-01-14 12:38:00 -05:00
Tony Tye 38744069df Make HSAILProgram::gpuNullDevice private
Change-Id: I822d1800eff0703a154dac997fe940d232eab542


[ROCm/clr commit: 2026a24438]
2021-01-14 11:12:14 -05:00