Граф коммитов
100 Коммитов
Автор SHA1 Сообщение Дата
Ben Sander 7adfdbe991 Add guideline for HIP_INIT_API
Change-Id: Ib8fa1e952f31158e9435dfc37ff23db9fda6fd7e


[ROCm/clr commit: 6fd03dde79]
2016-08-29 18:40:23 -05:00
Ben Sander ae336b6a6d Update supported API list
Change-Id: Idbc941e4464d200aca7ac3382060edc08ab94ef2


[ROCm/clr commit: a03a71badd]
2016-08-29 18:39:50 -05:00
Ben Sander 78cfa5f6d6 Refactor trace code for hipLaunchKernel.
- Use standard print functions for streams.
- Add HIP_INIT macro, for cases where we want to initialize HIP but not
  log an API (ihipPreKernelLaunch).

Change-Id: If43cf8a363d918bcd3722a2e6a965d4cfa2e03e7


[ROCm/clr commit: fa9b95838a]
2016-08-29 18:37:57 -05:00
Ben Sander f538d2e510 remove stray printf
Change-Id: Ie64778a83dfe684ffaab3c31bc3d09b713f825b9


[ROCm/clr commit: eb61114739]
2016-08-29 18:36:30 -05:00
Ben Sander f317725b7c Doc update. Describe memcpytosymbol, threadfence_system workarounds
[ROCm/clr commit: d76372a049]
2016-08-29 13:45:20 -05:00
Ben Sander 713eb5636d Remove cutnpaste check on uninitialized hsa status
Change-Id: Icc0256b9b1bd01d45cca4feb1106cfe7427bcd15


[ROCm/clr commit: 46c3ff52a6]
2016-08-28 16:35:27 -05:00
Ben Sander 40ca19440c Remove deprecated message from hipLaunchModuleKernel
Change-Id: I87675453ae4363e3340a9d1491bb00543fa8c6e0


[ROCm/clr commit: f7ee14e637]
2016-08-28 16:34:34 -05:00
Ben Sander 99340539a9 Add docs on porting driver API
[ROCm/clr commit: 8b8181df41]
2016-08-26 10:46:39 -05:00
Ben Sander 613cf84e5b Doc update to clarify supported / unsupported features
[ROCm/clr commit: 8d02cf466f]
2016-08-26 10:46:39 -05:00
Ben Sander a4bfccf628 Context update.
- Remove tls_deviceID.
- Add first passing test.

Change-Id: If3e2f254abf589028cfe4f9e6369745f04160de0


[ROCm/clr commit: a9bcee3d77]
2016-08-10 08:59:47 -05:00
Ben Sander f7c955104a Document workaround for parenthesis+macro+hipLaunchKernel
Change-Id: Ie04c99db92d6499ddde93028a96f9d8f72d3f992


[ROCm/clr commit: e23cd0dd3c]
2016-08-10 08:59:47 -05:00
Ben Sander 0c8ca4b37d Add initial context implementation.
APIs: hipInit, hipCtxCreate.
Track TLS default ctx.  Set deviceID now changes the ctx.
Add first context test.

Change-Id: If1cb9989b5a04a36147e25e84904336c7b6f3d88


[ROCm/clr commit: f19f2248bf]
2016-08-08 17:49:02 -05:00
Ben Sander c85f34bf8a Code cleanup, use camelCase where appropriate.
Change-Id: I5a7ec50df8bbb3e7a3b313c0b12e2dd55ae4a09c


[ROCm/clr commit: ac173c3ae8]
2016-08-08 14:54:38 -05:00
Ben Sander 4ef3cb1796 Coding guidelines update
Change-Id: Ib8d8da4c3897d157aeb26eb2e99718d66fd260b1


[ROCm/clr commit: 7c5a611df4]
2016-08-08 13:12:22 -05:00
Ben Sander e6dd8281d0 Move copy kernel templates into hip_memory.cpp
Change-Id: I862529f3fa8232372c6bacaa5d36f035bbdd32a1


[ROCm/clr commit: 6dbe554894]
2016-08-08 12:07:12 -05:00
Ben Sander 3ee6e7f8ab Split ihipCtx_t into ihipCtx_t and ihipDevice_t .
Major change to existing code base.
    Ctx holds streams, enables peers, and flags.
    Device holds accelerator, hsa-agent, device props.

Add hipCtx_t.

Add peer APIs that accept hipCtx_t (in addition to deviceId)

Compiles and passes directed tests.

Change-Id: Iddab1eb9edbf90caad2ef5959c6b811d658197f1


[ROCm/clr commit: d09b19bb6c]
2016-08-08 11:55:57 -05:00
Ben Sander 4c7160a134 Add initial/partial coding guidelines
Change-Id: Ifd8cb3ad74b15d3ab2f38c3daa038a2808af6fa9


[ROCm/clr commit: 694c0bad62]
2016-08-08 11:55:41 -05:00
Ben Sander e5300e2b40 Change Device->Ctx
Change ihipDevice_t -> ihipCtx_t (new)
Change ihipGetTlsDefaultDevice->ihipGetTlsDefaultCtx
Some other changes from device->ctx where appropriate.

Change-Id: I5c4ae93b2fd42c6303aa23d748eb166b7431925d


[ROCm/clr commit: 0d16565061]
2016-08-07 21:47:12 -05:00
Ben Sander aa43c9e006 Remove ihipStream_r::_device_index
Replace with direct pointer to device.  Cleaner, and prep
for transition to contexts.

Change-Id: I0e550f34412923d46c541c0a14bb7d29c3fd4b11


[ROCm/clr commit: 3c604b6430]
2016-08-07 20:47:06 -05:00
Ben Sander ffd5a709f6 Remove faulty assert for kernelCnt==0
Change-Id: I8a925c95f48e857c0a31f44561499e90dc6df552


[ROCm/clr commit: bb005d1755]
2016-08-01 13:38:47 -05:00
Ben Sander 381f67e067 Remove dead enqueueBarrier function.
Change-Id: Ib18fe6bd96ce24dbeb342961ddb5721f7d03f2b2


[ROCm/clr commit: f7ab82cb39]
2016-07-28 22:48:22 -05:00
Ben Sander a853d10446 Cleanup sync code.
Remove dead depFutures, enqueueBarrier call.
Rename some parms to reflect usage.
Add comments to better explain tricky parts of sync code.

Change-Id: I763296421d9c2b3b58fc8cef5f010b12ab49553c


[ROCm/clr commit: ef61aae878]
2016-07-27 18:31:11 -05:00
Ben Sander 058e927c9b Fix API string message for hipDeviceGetAttribute
Change-Id: I30f54627630c8ee835506be8c9921742bb68a43a


[ROCm/clr commit: f5118ce3cd]
2016-07-27 16:18:14 -05:00
Ben Sander 0ed0ad30da Doc update for FAQ and future RELEASE notes
Change-Id: I7e7c32d9a19fdaea0a0e41f1d4fa4652e53640f2


[ROCm/clr commit: 77be00e8d3]
2016-07-26 12:14:15 -05:00
Ben Sander 542948ad75 Doc update for README.md - add more intro text, example
Change-Id: I99b8eaacd6460dfdbdbc8ddba3fe589647d877e7


[ROCm/clr commit: 75d1f8c297]
2016-07-26 12:14:02 -05:00
Ben Sander 4094170fd7 Make HCC ignore register keyword
- (previously would emit a warning)
- Also tweak documentation.

Change-Id: I0f4f00f82f8cc53d420112570f2d7675535e6aea


[ROCm/clr commit: b9e48d6066]
2016-07-26 12:13:48 -05:00
Ben Sander 5586cc02b4 Update documentation.
- Add more detailed feature comparison HIP vs specific CUDA SDK revs.
- Remove reference to old codenames.
- Fix TOC in some md files.

Change-Id: If0f6a05dc61237c4710c4d4bf2d933d556dcaeae


[ROCm/clr commit: 4b3102b578]
2016-07-18 13:56:22 -05:00
Ben Sander 5edb4185a2 Use GRID_LAUNCH_VERSION define provided by HCC grid_launch.h
Change-Id: I5a7b31f13c4055cdca3a8854728d59db7dc5a7bb


[ROCm/clr commit: 5fecff5a59]
2016-06-21 23:52:25 -05:00
Ben Sander 050430789c Grid-launch updates to 2.0 and cleanup of old.
_ Use fields from GRID_LAUNCH_20 structure
  (See USE_GRID_LAUNCH_20 define, currently set to 0)
  "1" will require HCC support.
- Remove old DISABLE_GRID_LAUNCH support.

Change-Id: I584ce648d217251789a6283cf27feb24cb7dc8d1


[ROCm/clr commit: e27b5cc927]
2016-06-21 23:24:38 -05:00
Ben Sander 5e376bf121 Switch to hc_* coordinate builtins (replace amp_)
Change-Id: I0a8871f0c9f047eb45a7391fd032100af2bbd4e0


[ROCm/clr commit: fefc3f3f1e]
2016-06-21 23:22:38 -05:00
Ben Sander caf2bc8208 Fix test project names
Change-Id: I105c3759208ec832f3bdf6068029b4bfa2827909


[ROCm/clr commit: 20a164be6a]
2016-06-17 15:18:57 -05:00
Ben Sander 12b1c634ef Initial release notes for 0.95.
Change-Id: I6d43f643f4c6ecd4b4e4434c5cc1dfecf540a6d3


[ROCm/clr commit: c82cd5822c]
2016-06-17 15:18:57 -05:00
Ben Sander a03c51dc9e Clean up old work-week and USE_* refs
Change-Id: I929c979fa085f8e5205194cbccca46e9b5516aa9


[ROCm/clr commit: 44d117ba63]
2016-06-17 15:18:57 -05:00
Ben Sander b31b23ff1d Refactor directed test infrastructue.
- Add hierarchy.  Tests now live in directories, each with its own
  CMakeFiles.txt.  Reduces merge conflicts.
- Change make_hip_executable -> build_hip_executable.
- Refresh docs.
- Enable some tests that were previously built but not run.

Change-Id: I8c5de3c954400bf233904282b8b42861a2b7c536


[ROCm/clr commit: 3feb13c8f6]
2016-06-17 15:18:57 -05:00
Ben Sander d2d921f7be Fix hierchical tests. Set compiler before project to avoid loop
Change-Id: Icede4e76cb47820b39403a7f1ba3f4bd3f47ed03


[ROCm/clr commit: 883d733174]
2016-06-17 15:18:57 -05:00
Ben Sander ac73c9331c Resolve cmake infinite loop issue
Change-Id: I8af4eb8dee754c97b72c108d4613071b0de023bd


[ROCm/clr commit: debddd9b45]
2016-06-16 19:43:07 -05:00
Ben Sander e317f07cb3 Add NVCC implementation for hipPeeakAtLastError
[ROCm/clr commit: 7492351a3c]
2016-06-16 09:38:34 -05:00
Ben Sander 62c5658e93 remove old KERNELBEGIN/KERNELEND macros
[ROCm/clr commit: dbffc7bba2]
2016-06-16 09:38:07 -05:00
Ben Sander 4679da2c45 Add include guards for HIP_PLATFORM_NVCC
[ROCm/clr commit: c2f9fb32a1]
2016-06-16 09:37:10 -05:00
Ben Sander a8cba75ce4 Update launch_bounds test
[ROCm/clr commit: 46e27c7568]
2016-06-16 09:29:03 -05:00
Ben Sander c6ace6f647 Add first steps for CMake test hierarchy + initial launch_bounds.
[ROCm/clr commit: 71b9369256]
2016-06-16 08:41:32 -05:00
Ben Sander c46b2e7450 NVCC improvements.
- Complete translation tables for cudaError <-> hipError_t.
- Remove some odd errors that were not correctly translated or not used.
- Add HIPCHECK_API to test infrastructure.  Used for negative testing
  an API ; if a mismatch occurs it shows the expected return error
  code.  Can also print a warning rather than error.
- Enable hipMemoryAllocate on NV system, and review error coded.
- Add hipErrorName to nvcc.

Change-Id: I680427dcf32a5796d5913cf9e7f3b4c6f6b91599

Conflicts:
	tests/src/CMakeLists.txt

Bug fixes and improved docs for hipFree and hipHostFree.

    - Passing NULL pointer initialized runtime and return hipSuccess
      (not an error like before).
    - add negative test for this. (hipMemoryAllocate, improved)
    - Match NVCC errors for invalid pointers, add to test.
    - Update hipFree and hipHostFree docs.
    - hipGetDevicePointer always set *devicePointer=NULL, even for
      invalid flags.
    - Gate shared memory usage on specific HCC work-week.

Change-Id: I533b4fd3280a3d6cdbf05eb768976f0c7506c012


[ROCm/clr commit: 6a2a140f34]
2016-06-16 06:13:51 +05:30
Ben Sander a34e3be329 move/update API list
Change-Id: I90457b90bbcb2a3309bf65a94a25be69af38f261


[ROCm/clr commit: b73bdb7e07]
2016-05-16 15:19:07 -05:00
Ben Sander 53892f52ae Update README.md
[ROCm/clr commit: ffd7511808]
2016-05-16 14:09:46 -05:00
Ben Sander c2a2fa029b Update release notes for 0.86
Change-Id: I60eb5691aec35fad714aac38deb3c4eccf7ae12a


[ROCm/clr commit: 98e04c7a83]
2016-05-13 12:40:31 +05:30
Ben Sander 0b9fcc8ea3 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/clr commit: b8df982dcd]
2016-05-03 11:16:09 -05:00
Ben Sander 76e08e3ea1 libstdc++ is default
[ROCm/clr commit: a35e995244]
2016-05-03 11:14:27 -05:00
Ben Sander 81f7559a37 doc update, add proposed .86 release notes
[ROCm/clr commit: c40b212430]
2016-05-03 11:11:04 -05:00
Ben Sander c578bb72ef Update porting guide docs on -stdlib
[ROCm/clr commit: 72f7a15e54]
2016-05-03 09:20:41 -05:00
Ben Sander a079847536 comment change
[ROCm/clr commit: 07b5785da2]
2016-05-03 08:33:35 -05:00
Ben Sander 18635995af add fallback to libc++
[ROCm/clr commit: 6a960aff38]
2016-05-02 23:50:39 -05:00
Ben Sander e6ec2439ec Link test with libc++
[ROCm/clr commit: 8cce8dbe61]
2016-05-02 23:38:43 -05:00
Ben Sander ef3273c1b1 add make_hip_executable_libcpp
[ROCm/clr commit: c79dad8000]
2016-05-02 23:32:52 -05:00
Ben Sander 41c57d1e00 Merge branch 'privatestaging' into grid_launch
[ROCm/clr commit: 20043d602e]
2016-05-02 18:38:20 -05:00
Ben Sander b578915e89 Merge branch 'p2p' into privatestaging
[ROCm/clr commit: caadac1005]
2016-05-02 13:48:06 -05:00
Ben Sander 183aaa5888 Merge branch 'privatestaging' into p2p
[ROCm/clr commit: 230b6546b5]
2016-05-02 13:38:01 -05:00
Ben Sander eaf4e4a0ee PASS with warning if not enough GPUs detected.
[ROCm/clr commit: a398cd4cda]
2016-05-02 13:37:14 -05:00
Ben Sander 7f90e11724 Explicitly include <string>
[ROCm/clr commit: aea31ad4e1]
2016-05-02 12:49:53 -05:00
Ben Sander d7933df2d3 Use hipconfig to determine platform
[ROCm/clr commit: c5bec313ee]
2016-05-02 11:33:22 -05:00
Ben Sander 070b88766f Merge branch 'privatestaging' into p2p
[ROCm/clr commit: 79983a1f4b]
2016-05-02 11:10:10 -05:00
Ben Sander e6832413fb Add clang-hipify as optional make step
[ROCm/clr commit: 83cf3ed2b5]
2016-05-02 10:20:00 -05:00
Ben Sander fb2a9f66fc split INSTALL.md into separate file
[ROCm/clr commit: 5d7f1682f4]
2016-05-02 10:19:46 -05:00
Ben Sander 445ca0c7ec merge
[ROCm/clr commit: 563591b065]
2016-04-28 18:24:33 -05:00
Ben Sander f5819ddcd5 enable hipHostRegister
[ROCm/clr commit: 9e36ee9b95]
2016-04-28 17:54:03 -05:00
Ben Sander 2a2bfb063a Doc update
[ROCm/clr commit: 06df8bbfbc]
2016-04-28 17:41:11 -05:00
Ben Sander 1c96a8215c Add tip on making local HIP (mostly for HIP devs)
[ROCm/clr commit: 87c355f09d]
2016-04-28 17:41:11 -05:00
Ben Sander 65ea6991e0 add hostname
[ROCm/clr commit: 0c636007a2]
2016-04-28 17:41:11 -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
Ben Sander 08721a2fda Doc update
[ROCm/clr commit: 7f1bd9e1e5]
2016-04-27 17:45:14 -05:00
Ben Sander b4bd9d851e Add tip on making local HIP (mostly for HIP devs)
[ROCm/clr commit: 26b87d5faf]
2016-04-27 11:55:09 -05:00
Ben Sander f000ced85c add hostname
[ROCm/clr commit: 31f41ba52a]
2016-04-25 15:13:23 -05:00
Ben Sander 5a8656b418 build hipHostRegister but dont run it
[ROCm/clr commit: 3c7a52971e]
2016-04-19 11:56:12 -05:00
Ben Sander 0f4bd3ad3a Fix hipDeviceReset synchronization
[ROCm/clr commit: ccf2c1c323]
2016-04-19 11:56:12 -05:00
Ben Sander 810f390cfe Set chicken bits to 0.
[ROCm/clr commit: b3c2d906db]
2016-04-19 11:56:12 -05:00
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 10d42fa7cc Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/clr commit: 1ac93489b9]
2016-04-18 21:51:13 -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 66a6cca54d test update
[ROCm/clr commit: 3301deb07c]
2016-04-17 07:54:39 -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 a77d6342a8 fix direction of peer enable/disable APIs
- Enable(peerId) makes memory physically located on peer visible to
current device.


[ROCm/clr commit: 4e0a1e1869]
2016-04-17 07:38:05 -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
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
Ben Sander 2a311f25ef Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/clr commit: 0cdac15fa4]
2016-04-14 07:19:20 -05:00
Ben Sander 9ff4294869 update README for new make/installation steps, new FAQ
[ROCm/clr commit: 489e76e584]
2016-04-14 07:19:07 -05:00
Ben Sander 70c75c0eed Fix HIP_PATH, CHECK macro in samples.
[ROCm/clr commit: 830527bfdc]
2016-04-13 17:37:39 -05:00
Ben Sander b2237cb953 add hcc dialects sample
[ROCm/clr commit: 8736d77818]
2016-04-13 17:32:38 -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 0861e7a635 add simple negative P2P tests
[ROCm/clr commit: 2f0c589ffe]
2016-04-11 13:46:53 -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
Ben Sander 76c49bbaf4 Clean up disable.
Add USE_HCC_LOCK (disabled)
Disable USE_PEER_TO_PEER.


[ROCm/clr commit: efffb0ed86]
2016-04-11 09:09:36 -05:00
Ben Sander 39cccf94ef fix peer query order
[ROCm/clr commit: a894ca3abb]
2016-04-11 07:58:59 -05:00
Ben Sander f177c8805e add simple negative P2P tests
[ROCm/clr commit: 1acd16eb5d]
2016-04-11 07:58:59 -05:00
Ben Sander 025938b1de 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: 9e7efd7c65]
2016-04-11 07:58:59 -05:00
Ben Sander ae8ed57c30 Improve P2P test.
- Ensure proper device is set before each command.

- Add command line switches:
    +bool p_memcpyWithPeer = false; // use the peer device for the P2P copy
    +bool p_mirrorPeers = false; // in addition to mapping current to peer
            space, map peer to current space.
    +int  p_peerDevice = -1;  // explicly specify which peer to use, else
use p_gpuDevice + 1.


[ROCm/clr commit: b039292a8c]
2016-04-11 07:58:58 -05:00
Ben Sander 2d90324c09 Improve P2P test.
Add option to select which device does the copy.


[ROCm/clr commit: b8e17d52dd]
2016-04-11 07:58:58 -05:00