AI/rocm-systems
2
0
Bifurcation 0
Code Tickets Demandes d'ajout Actions Paquets Projets Publications Wiki Activité
76 333 Révisions 3 Branches 0 Étiquette
develop
Graphe des révisions

76333 Révisions

Cette branche
Cette branche
Toutes les branches
Auteur SHA1 Message Date
Sean Keely a427fde26a Cleanup Signal interfaces for doorbells. 
Create an interface for doorbell signals to reduce code duplication.
No functional changes.

Change-Id: I101a8997dd582ff99e1537758c804b21fe3bb6af


[ROCm/ROCR-Runtime commit: d2e70bb999]
 2017-11-28 22:12:19 -06:00
Alex Voicu 4d18ad9ebe Fix compiler version check. 
[ROCm/clr commit: 93e595c267]
 2017-11-29 03:05:53 +00:00
Alex Voicu 93e595c267 Fix compiler version check. 2017-11-29 03:05:53 +00:00
Alex Voicu c58a083e96 Fix compiler version check. 
[ROCm/hip commit: b881cf713c]
 2017-11-29 03:05:53 +00:00
Alex Voicu b881cf713c Fix compiler version check. 2017-11-29 03:05:53 +00:00
Sylvain Jeaugey 63ab6df5b3 Merge pull request #119 from sclarkson/master 
Fix tests: call cudaHostUnregister on the host pointer instead of the device pointer.

[ROCm/rccl commit: 286916a1a3]
 2017-11-28 18:41:26 -08:00
Sylvain Jeaugey 286916a1a3 Merge pull request #119 from sclarkson/master 
Fix tests: call cudaHostUnregister on the host pointer instead of the device pointer.
 2017-11-28 18:41:26 -08:00
Alex Voicu 0636d6a976 Add missing file. 
[ROCm/clr commit: e305d3fc94]
 2017-11-29 02:16:44 +00:00
Alex Voicu e305d3fc94 Add missing file. 2017-11-29 02:16:44 +00:00
Alex Voicu 00e435bda1 Add missing file. 
[ROCm/hip commit: 3ed8897a5a]
 2017-11-29 02:16:44 +00:00
Alex Voicu 3ed8897a5a Add missing file. 2017-11-29 02:16:44 +00:00
Sean Keely b93ffafdc7 Pull from github (tstellar): 
Prefer using memfd_create() for the ring buffer.

We were using /dev/shm, but this won't work on systems that
either don't have /dev/shm or have mounted it with noexec, because
for everything other than gfx700 we map the ring buffer with PROT_EXEC.

memfd_create() is Linux specific and was added in Linux 3.17, so we
will fallback to using /dev/shm on systems where memfd_create() is
not available.

Change-Id: I58fb533eebc362f6d29dc3e316a80801014d50e8
 2017-11-28 20:47:12 -05:00
Sean Keely 495c1da5f3 Pull from github (tstellar): 
Prefer using memfd_create() for the ring buffer.

We were using /dev/shm, but this won't work on systems that
either don't have /dev/shm or have mounted it with noexec, because
for everything other than gfx700 we map the ring buffer with PROT_EXEC.

memfd_create() is Linux specific and was added in Linux 3.17, so we
will fallback to using /dev/shm on systems where memfd_create() is
not available.

Change-Id: I58fb533eebc362f6d29dc3e316a80801014d50e8


[ROCm/ROCR-Runtime commit: b93ffafdc7]
 2017-11-28 20:47:12 -05:00
Alex Voicu 6b21218303 Fix oversight in selection mechanism which led to erroneous code to be compiled for the grid_launch_GGL component. 
[ROCm/clr commit: 37c1811b2a]
 2017-11-29 01:37:52 +00:00
Alex Voicu 37c1811b2a Fix oversight in selection mechanism which led to erroneous code to be compiled for the grid_launch_GGL component. 2017-11-29 01:37:52 +00:00
Alex Voicu b996310710 Fix oversight in selection mechanism which led to erroneous code to be compiled for the grid_launch_GGL component. 
[ROCm/hip commit: faa546d194]
 2017-11-29 01:37:52 +00:00
Alex Voicu faa546d194 Fix oversight in selection mechanism which led to erroneous code to be compiled for the grid_launch_GGL component. 2017-11-29 01:37:52 +00:00
Sean Keely 4b603e803d Improve loop variables. 
Derived from github pull request by folklore1984.

Change-Id: I70cd3da131691543fed8bf913d6245d41c49280d
 2017-11-28 20:36:22 -05:00
Sean Keely 37132e4a21 Improve loop variables. 
Derived from github pull request by folklore1984.

Change-Id: I70cd3da131691543fed8bf913d6245d41c49280d


[ROCm/ROCR-Runtime commit: 4b603e803d]
 2017-11-28 20:36:22 -05:00
Sean Keely 5872b618de Pull from github (pmargheritta): 
Corrected semantics used in hsa_queue_load_write_index_relaxed.

The semantics that was used in hsa_queue_load_write_index_relaxed
didn't seem to match the name of the function.
I also removed a useless return keyword.

Change-Id: If3819d38fb367f122fc382edf8ee3771a23279ae
 2017-11-28 20:35:50 -05:00
Sean Keely 7ed62f815f Pull from github (pmargheritta): 
Corrected semantics used in hsa_queue_load_write_index_relaxed.

The semantics that was used in hsa_queue_load_write_index_relaxed
didn't seem to match the name of the function.
I also removed a useless return keyword.

Change-Id: If3819d38fb367f122fc382edf8ee3771a23279ae


[ROCm/ROCR-Runtime commit: 5872b618de]
 2017-11-28 20:35:50 -05:00
Alex Voicu cdac21c81a Choose whether or not to use functional grid_launch based on the version of HCC used to compile. 
[ROCm/clr commit: c6ab6f292b]
 2017-11-29 00:17:44 +00:00
Alex Voicu c6ab6f292b Choose whether or not to use functional grid_launch based on the version of HCC used to compile. 2017-11-29 00:17:44 +00:00
Alex Voicu dd8a589893 Choose whether or not to use functional grid_launch based on the version of HCC used to compile. 
[ROCm/hip commit: 89e9399427]
 2017-11-29 00:17:44 +00:00
Alex Voicu 89e9399427 Choose whether or not to use functional grid_launch based on the version of HCC used to compile. 2017-11-29 00:17:44 +00:00
foreman 8917c073fa P4 to Git Change 1487815 by emankov@em-hsa-lightning on 2017/11/28 16:19:33 
SWDEV-134396 - cl_amd_assembly_program extension support. Part 2 of 4. Rocm Runtime: Compiler invocation.

	precheckin:
	http://ocltc.amd.com:8111/viewModification.html?modId=94552&personal=true&init=1&tab=vcsModificationBuilds

	reviewed by:
	German Andryeyev

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclEnums.h#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#77 edit


[ROCm/clr commit: a5884cdbf4]
 2017-11-28 16:25:11 -05:00
foreman a5884cdbf4 P4 to Git Change 1487815 by emankov@em-hsa-lightning on 2017/11/28 16:19:33 
SWDEV-134396 - cl_amd_assembly_program extension support. Part 2 of 4. Rocm Runtime: Compiler invocation.

	precheckin:
	http://ocltc.amd.com:8111/viewModification.html?modId=94552&personal=true&init=1&tab=vcsModificationBuilds

	reviewed by:
	German Andryeyev

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclEnums.h#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#77 edit
 2017-11-28 16:25:11 -05:00
Oak Zeng cce57cec26 Cosmetic changes in events.c 
Change-Id: Idecb8eede8811020b3af51cbc71da74849029c82
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
 2017-11-28 15:20:51 -05:00
Oak Zeng 90f35469d6 Cosmetic changes in events.c 
Change-Id: Idecb8eede8811020b3af51cbc71da74849029c82
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>


[ROCm/ROCR-Runtime commit: cce57cec26]
 2017-11-28 15:20:51 -05:00
Alex Voicu e85f49a57e Remove leftover agent allocated globals. 
[ROCm/clr commit: 45a9f4f7b1]
 2017-11-28 19:56:04 +00:00
Alex Voicu 45a9f4f7b1 Remove leftover agent allocated globals. 2017-11-28 19:56:04 +00:00
Alex Voicu 8fcd85757a Remove leftover agent allocated globals. 
[ROCm/hip commit: 5aeb5dcd6f]
 2017-11-28 19:56:04 +00:00
Alex Voicu 5aeb5dcd6f Remove leftover agent allocated globals. 2017-11-28 19:56:04 +00:00
Alex Voicu abf92dd6e7 Change memset kernel to use memcpy instead of placement new. Simplify indexers. 
[ROCm/clr commit: d5c8de3f41]
 2017-11-28 19:45:47 +00:00
Alex Voicu d5c8de3f41 Change memset kernel to use memcpy instead of placement new. Simplify indexers. 2017-11-28 19:45:47 +00:00
Alex Voicu 9668003fe3 Change memset kernel to use memcpy instead of placement new. Simplify indexers. 
[ROCm/hip commit: 6e4ca3fbb4]
 2017-11-28 19:45:47 +00:00
Alex Voicu 6e4ca3fbb4 Change memset kernel to use memcpy instead of placement new. Simplify indexers. 2017-11-28 19:45:47 +00:00
Alex Voicu 914acbe88f Re-sync with upstream and re-factor platform global management for texture references. 
[ROCm/clr commit: 6a0efb7ed2]
 2017-11-28 19:15:29 +00:00
Alex Voicu 6a0efb7ed2 Re-sync with upstream and re-factor platform global management for texture references. 2017-11-28 19:15:29 +00:00
Alex Voicu aef26d3477 Re-sync with upstream and re-factor platform global management for texture references. 
[ROCm/hip commit: 02c2bfc7ef]
 2017-11-28 19:15:29 +00:00
Alex Voicu 02c2bfc7ef Re-sync with upstream and re-factor platform global management for texture references. 2017-11-28 19:15:29 +00:00
Alex Voicu 579a3187da Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe 
# Conflicts:
#	src/hip_module.cpp


[ROCm/clr commit: d37a5a6008]
 2017-11-28 17:29:11 +00:00
Alex Voicu d37a5a6008 Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe 
# Conflicts:
#	src/hip_module.cpp
 2017-11-28 17:29:11 +00:00
Alex Voicu 11f7d895f4 Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe 
# Conflicts:
#	src/hip_module.cpp


[ROCm/hip commit: dc67ca3feb]
 2017-11-28 17:29:11 +00:00
Alex Voicu dc67ca3feb Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe 
# Conflicts:
#	src/hip_module.cpp
 2017-11-28 17:29:11 +00:00
Maneesh Gupta 621cc5e5ca Fix float2int rounding functions 
Change-Id: I67943859a6344c5eec0eaa23418c9b802ef72468


[ROCm/clr commit: cc418da654]
 2017-11-28 17:23:43 +00:00
Maneesh Gupta cc418da654 Fix float2int rounding functions 
Change-Id: I67943859a6344c5eec0eaa23418c9b802ef72468
 2017-11-28 17:23:43 +00:00
Maneesh Gupta 3b25286003 Fix float2int rounding functions 
Change-Id: I67943859a6344c5eec0eaa23418c9b802ef72468


[ROCm/hip commit: 265c3b224e]
 2017-11-28 17:23:43 +00:00
Maneesh Gupta 265c3b224e Fix float2int rounding functions 
Change-Id: I67943859a6344c5eec0eaa23418c9b802ef72468
 2017-11-28 17:23:43 +00:00
Alex Voicu a59daf78d6 This actually (tries) to do the right thing all the way, by using memcpy for bitcasting, and not rely on undefined behaviour of a different flavour as a substitute for the original undefined behaviour. Note that the compiler will (should) optimise down to the same emitted code, since this is a pattern it understands. 
[ROCm/clr commit: bb35299560]
 2017-11-28 17:23:06 +00:00