Commit grafiek

183 Commits

Auteur SHA1 Bericht Datum
Jack Chung 786e509ca7 Fix math functions so they can be used on host codes as well
Add __host__ for some math functions to fix the following tests:

- hipSinglePrecisionMathHost
- hipDobulePrecisionMathHost


[ROCm/clr commit: 5e86860c05]
2016-05-06 08:09:52 +08:00
Ben Sander 41c57d1e00 Merge branch 'privatestaging' into grid_launch
[ROCm/clr commit: 20043d602e]
2016-05-02 18:38:20 -05:00
Ben Sander f5819ddcd5 enable hipHostRegister
[ROCm/clr commit: 9e36ee9b95]
2016-04-28 17:54:03 -05:00
Ben Sander cb7c61643b remove kalmar_defines.h
[ROCm/clr commit: a16c58ed46]
2016-04-28 17:40:17 -05:00
Ben Sander a73068d640 remove hacks to disable math or LDG functions.
[ROCm/clr commit: 9363e495e1]
2016-04-28 14:14:22 -05:00
Ben Sander 62da82d48c Properly pair #if/#endif
[ROCm/clr commit: c60614eca5]
2016-04-28 13:43:32 -05:00
Ben Sander b31e27f244 merge fix
[ROCm/clr commit: 5c098d5852]
2016-04-28 13:24:40 -05:00
Ben Sander b2608d2949 hipcc uses -stdlib=stdlibc++ by default.
hipcc switches to -stdlib=libc++ if user requests it.
hack to disable LDG.


[ROCm/clr commit: 06e54694c5]
2016-04-28 13:17:49 -05:00
Jack Chung e263765fa4 Fix compilation error in hipSinglePrecisionMathHost test
[ROCm/clr commit: a5508ae185]
2016-04-27 17:46:27 -05:00
Aditya Atluri 8241a3dd75 changed to guard from hc.hpp
[ROCm/clr commit: ec8cedc70e]
2016-04-27 17:46:27 -05:00
bwicakso 8c51afe53b Merge remote-tracking branch 'refs/remotes/origin/privatestaging' into kernel_synchronization
[ROCm/clr commit: 5552301de2]
2016-04-25 14:43:28 -05:00
bwicakso f4b7559be8 Update with original
[ROCm/clr commit: a849321bd9]
2016-04-25 14:42:35 -05:00
bwicakso 4efcfdb83c Merge remote-tracking branch 'refs/remotes/origin/privatestaging' into kernel_synchronization
[ROCm/clr commit: 4aca1babe8]
2016-04-25 13:57:28 -05:00
bwicakso 64867da465 Merge from original
[ROCm/clr commit: 7175ca8824]
2016-04-25 13:55:44 -05:00
Aditya Atluri 266d13c9ce Fixed git spills
[ROCm/clr commit: c404f60621]
2016-04-22 09:19:05 -05:00
Aditya Atluri ab3a1e99c5 added workweek to hip_ldg
[ROCm/clr commit: a2bc6ebc9f]
2016-04-22 09:14:26 -05:00
Maneesh Gupta 03014e8a1d Merge branch 'release_0.84.00' into privatestaging
Conflicts:
	include/hcc_detail/hip_runtime.h
	src/hip_hcc.cpp


[ROCm/clr commit: 02e6fc27f4]
2016-04-22 10:55:58 +05:30
Aditya Atluri b426b5b8b6 reorg make_datatype feature
[ROCm/clr commit: 48f3762160]
2016-04-21 14:51:19 -05:00
Aditya Atluri 23a91cd8aa added full data type support for __ldg
[ROCm/clr commit: 3aac6d45ad]
2016-04-21 11:17:26 -05:00
bwicakso 90fffbca82 Fix for kernel synchronization
The completion future of a particular kernel is lost if there are
multiple kernels in the stream. This can cause a racing condition where
the signal associated with the unreferenced completion_future might get
released by hcc runtime.


[ROCm/clr commit: 6773a64b22]
2016-04-20 15:51:39 -05:00
Aditya Atluri 91338214a6 added copyright for ldg
[ROCm/clr commit: f46e1bcf0e]
2016-04-20 12:28:02 -05:00
Aditya Atluri b857720440 added support for __ldg
[ROCm/clr commit: b493eac7e0]
2016-04-20 12:25:40 -05:00
pensun fe9234e9df update API trace information for hipLaunchKernel
[ROCm/clr commit: 517008f98b]
2016-04-20 09:57:55 -05:00
pensun 91286fe84a Merge branch 'release_0.84.00' of https://github.com/AMDComputeLibraries/HIP-privatestaging into release_0.84.00
[ROCm/clr commit: f0b0bc672a]
2016-04-20 09:48:52 -05:00
pensun 8be7a1b859 update hipLaunchKernel API trace information
[ROCm/clr commit: f8ad557864]
2016-04-20 09:48:35 -05:00
Ben Sander 0f4bd3ad3a Fix hipDeviceReset synchronization
[ROCm/clr commit: ccf2c1c323]
2016-04-19 11:56:12 -05:00
Jack Chung f1a290e07a Fix compilation error in hipSinglePrecisionMathHost test
[ROCm/clr commit: 4431a93c2c]
2016-04-19 23:17:09 +08:00
Maneesh Gupta c99285c5fb Prefix HIP includes with hip/
[ROCm/clr commit: c4cc76398c]
2016-04-19 15:02:12 +05:30
Ben Sander 074fa8c53b Add experimental notes around p2p
[ROCm/clr commit: 21d733b2e7]
2016-04-18 23:52:42 -05:00
Ben Sander 7cbe4a1651 Add USE_HCC_LOCK_API.
Default off, if set will compile assuming HCC lock APIs exist.


[ROCm/clr commit: 9329fb8c92]
2016-04-18 23:50:52 -05:00
Ben Sander 57a4505e77 Fixes for P2P and hipDeviceReset
- devicereset would lose track of default stream and thus subsequent
  synchronization calls might not actually sychronize.
- Also deviceReset now correctly frees streams.
- fix waits in P2P staging copy - first phase (Device0-to-Staging) must
  wait for second phase (Staging to Device1) to finish draining the
  buffer.


[ROCm/clr commit: 6abfa13c34]
2016-04-18 20:49:33 -05:00
Ben Sander e92dbaeecd Move HIP_HCC define to CMake
[ROCm/clr commit: f9a31e28ad]
2016-04-17 07:40:04 -05:00
Ben Sander dd323f5e31 Merge branch 'privatestaging' into p2p
Conflicts:
	include/hcc_detail/hip_hcc.h
	src/hip_hcc.cpp


[ROCm/clr commit: 8d26dfcde3]
2016-04-17 06:46:52 -05:00
Aditya Atluri 2dc71a9713 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/clr commit: 95e9de0946]
2016-04-16 17:10:32 -05:00
Aditya Atluri f0a9d95d55 Corrected Memcpydefault
[ROCm/clr commit: dc61929a3d]
2016-04-16 17:10:13 -05:00
Ben Sander 942509d66e P2P Update.
- add P2P staging buffer copy.
- If copy device does not have sufficient access permissions, fall back
  to staging buffer.
- improve docs for which copy device is used.


[ROCm/clr commit: c3bd85595d]
2016-04-16 10:18:56 -05:00
streamhsa 419d46f901 Add __ldg
[ROCm/clr commit: 0426564a7b]
2016-04-16 21:12:09 +08:00
Maneesh Gupta 97b91267b0 Bump min required hcc to workweek 16155
[ROCm/clr commit: 1cd52f5192]
2016-04-16 14:49:10 +05:30
Aditya Atluri 1b9d8c46e1 changed to guard from hc.hpp
[ROCm/clr commit: 85c04d8a7d]
2016-04-15 11:21:45 -05:00
Aditya Atluri a9401cba2e improved error returns for hipHostRegister/UnRegister functions
[ROCm/clr commit: e8902a6e20]
2016-04-15 10:42:31 -05:00
pensun 394ded007d Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/clr commit: 1ab9b0ac71]
2016-04-14 09:02:16 -05:00
Aditya Atluri 0eab4527d7 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/clr commit: c3b854fba4]
2016-04-14 09:17:30 -05:00
Aditya Atluri 8fdf04a64b Enabling make_* device code
[ROCm/clr commit: 12e24f4816]
2016-04-14 09:17:13 -05:00
pensun 84dbc09fe6 Add missing cudaMemsetAsync transformation
[ROCm/clr commit: 596e8e4e4e]
2016-04-14 09:02:02 -05:00
Maneesh Gupta 8ccfb15f73 Add hip soft-link to include for migrating to new include format
[ROCm/clr commit: 0dfb9cddad]
2016-04-14 16:37:27 +05:30
Jack Chung 5499f15f62 Add missing USE_PEER_TO_PEER macro definition
[ROCm/clr commit: fe0e5f3541]
2016-04-13 13:56:26 +08:00
Aditya Atluri aa048f2fe1 Removed pragma once
[ROCm/clr commit: 3b79b86a96]
2016-04-12 09:22:03 -05:00
Aditya Atluri f381fbb2be added C guard to hip_runtime.h
[ROCm/clr commit: 42df534354]
2016-04-11 13:01:02 -05:00
Ben Sander d3356ba99f Merge branch 'p2p' of https://github.com/AMDComputeLibraries/HIP-privatestaging into p2p
Conflicts:
	RELEASE.md
	include/hcc_detail/hip_hcc.h
	samples/1_Utils/hipInfo/hipInfo.cpp
	src/hip_hcc.cpp
	src/hip_peer.cpp


[ROCm/clr commit: 1cc0ea86a1]
2016-04-11 09:17:27 -05:00
Ben Sander 9bf70214f3 P2p checkpoint.
- set USE_PEER_TO_PEER=3 (requires HCC "am_memtracker_update_peers")
- when enabling peer, turn it on for previously allocated memory.
- hipDeviceCanAccessPeer is no longer self-ware (self does not qualify
  as a peer)
- device peerlist always includes self, so when we call allow_access
  we never remove self access.
- hipDeviceReset() removes old peer mappings.


[ROCm/clr commit: 5af4c901c6]
2016-04-11 12:52:18 -05:00