Commit Graph

363 Commits

Author SHA1 Message Date
Maneesh Gupta 44cdc3c6a5 Initial (non-default) support for shared library HIP
[ROCm/hip commit: 9de57129b4]
2016-04-01 15:45:32 +05:30
Maneesh Gupta 010529ecf5 Change HCC_DIR -> HCC_HOME, HSA_DIR -> HSA_PATH and HIP_INSTALL_PATH -> CMAKE_INSTALL_PREFIX
[ROCm/hip commit: 06dd3444b2]
2016-04-01 13:48:37 +05:30
Maneesh Gupta 02dfa83d06 Fix path comparison for install components in cmake
[ROCm/hip commit: 6dec2306da]
2016-04-01 12:13:22 +05:30
Aditya Atluri 70c1ac9285 added device math functions
[ROCm/hip commit: 26985b746b]
2016-03-31 12:29:19 -05:00
Aditya Atluri c750820adf Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: 6224d7495e]
2016-03-31 04:45:23 -05:00
Maneesh Gupta 2f95f9b81c Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: 3237115df3]
2016-03-31 21:16:39 +05:30
Maneesh Gupta c4205e5074 Cleaned up cmake
[ROCm/hip commit: a8767f71c1]
2016-03-31 17:42:29 +05:30
Aditya Atluri fe0f4e8bc2 moved cpp specific device code from headers to source
[ROCm/hip commit: 72c72d8748]
2016-03-31 04:45:00 -05:00
Aditya Atluri 2514b57970 Added directory for stress testing
[ROCm/hip commit: ea3ebcb3de]
2016-03-31 02:14:12 -05:00
Aditya Atluri c7d4da60ad Fixed failing tests
[ROCm/hip commit: 3f5ba43837]
2016-03-30 13:00:44 -05:00
Aditya Atluri 59e056e3e9 Revert to multiple output files than single .a lib
[ROCm/hip commit: 9de4c04a0a]
2016-03-30 07:54:18 -05:00
Aditya Atluri afd8f2bcfc C guarding the apis
[ROCm/hip commit: 496da0aabd]
2016-03-30 06:08:50 -05:00
Aditya Atluri 3683e2a3bd Moved flag to hip_runtime.h
[ROCm/hip commit: da1d9caf6b]
2016-03-30 03:32:39 -05:00
Maneesh Gupta a135881829 Implement more complex HCC, HSA directory selection logic
[ROCm/hip commit: 5684cd67b9]
2016-03-30 13:58:38 +05:30
Aditya Atluri f052a2752a Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: 39af5d9caf]
2016-03-29 11:18:09 -05:00
Ben Sander 55bd3a8d0c rename to hipMultiThreadDevice for consistency
[ROCm/hip commit: a37a019b01]
2016-03-29 17:33:29 -05:00
Ben Sander 321933c08f Test improvements
- partition hipThreadSafeDevice into smaller pieces.
- Add debug to hipMultiThreadStream.
- print more precision when mismatch detected.
- enable more tests in CMakeFiles.txt.


[ROCm/hip commit: 23e5eb8912]
2016-03-29 17:29:31 -05:00
Ben Sander 2543332f03 Inline some new string functions.
[ROCm/hip commit: f8a4483a55]
2016-03-29 17:28:27 -05:00
Ben Sander 24f82925bb Add runtime switch to control HIP_ATP_MARKER
Only generate the function strings if requested at
compile-time && runtime.


[ROCm/hip commit: 740b730cac]
2016-03-29 17:27:30 -05:00
Ben Sander 5e3431ecc0 include codexl marker path, if found
[ROCm/hip commit: 2348091b62]
2016-03-29 17:26:44 -05:00
Ben Sander abf24c2147 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: ce4052f09c]
2016-03-29 17:12:36 -05:00
Ben Sander 1f8e0e2e72 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: fb7862dba3]
2016-03-29 14:43:35 -05:00
Aditya Atluri 024fa0b78b Update README.md
[ROCm/hip commit: 1991fb5c92]
2016-03-29 14:23:41 -05:00
Aditya Atluri 83df7785c8 Update README.md
[ROCm/hip commit: 340560cbc3]
2016-03-29 14:11:10 -05:00
Aditya Atluri ffe185d731 Calling intrinsics from global kernel
[ROCm/hip commit: 61cd2bb399]
2016-03-29 11:17:55 -05:00
Aditya Atluri d0b0cda704 added host flags to hipDeviceBody test
[ROCm/hip commit: f518d0f818]
2016-03-29 09:27:57 -05:00
Aditya Atluri b7284988d6 Added tests for running device code from a difference source file
[ROCm/hip commit: 2f46ada042]
2016-03-29 09:22:31 -05:00
Ben Sander 9e50af9124 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
Conflicts:
	include/hcc_detail/trace_helper.h


[ROCm/hip commit: 756c0edf9b]
2016-03-29 05:56:03 -05:00
Aditya Atluri 79fea63bb7 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: 4584fb4453]
2016-03-29 02:28:20 -05:00
streamhsa 1d55744e91 change makefile for samples
[ROCm/hip commit: d0f0bf5c8e]
2016-03-29 16:02:09 +08:00
Aditya Atluri 811d6d52ea Not using classes inside headers
[ROCm/hip commit: f01810183b]
2016-03-29 02:27:51 -05:00
Ben Sander 630ef59d7b Tweak thread-safe implementation.
introduce LockedAccessor option so destructor does not unlock.
Allows locks to exist across function boundaries, required
for hipLaunchKernel macro which has several unusual requirements.
(including C comppatibility, must use variadic macro, more).


[ROCm/hip commit: 8635863724]
2016-03-28 21:41:47 -05:00
Siu Chi Chan 105e8e8708 Merge pull request #19 from AMDComputeLibraries/fix_static_lib_link
Various fixes in HIP exposed by linking to static library

[ROCm/hip commit: cc0bfcb2b2]
2016-03-28 22:40:04 -04:00
scchan 63636b07a8 remove the --hipcc_explicit_lib
[ROCm/hip commit: 2ddb8fface]
2016-03-28 13:56:23 -05:00
scchan 24f214e92a turn off ONE_OBJECT_FILE since we are building a static library
[ROCm/hip commit: 00ae9531a7]
2016-03-28 12:56:15 -05:00
Maneesh Gupta e4227684b2 Fixed cmake not honoring user specified HIP_INSTALL_DIR
[ROCm/hip commit: 40cc748678]
2016-03-28 22:23:27 +05:30
Maneesh Gupta 513a91d25c Improve cmake settings
[ROCm/hip commit: 1806979e72]
2016-03-28 21:55:03 +05:30
Ben Sander 9e3ac64c54 Stream thread-safe checkpoint.
Moving data structures to critical / protected section.


[ROCm/hip commit: 3f18bab2c7]
2016-03-28 09:46:40 -05:00
scchan 8afe22a3e9 add inline keyword to all the template functions
[ROCm/hip commit: 0087ee405e]
2016-03-28 09:18:38 -05:00
Ben Sander 0f11beb328 fix ihipLogStatus so status arg only evaluated once
[ROCm/hip commit: 3aed9d3b19]
2016-03-28 05:23:53 -05:00
Ben Sander c9b5b99078 Stream thread-safe checkpoint.
[ROCm/hip commit: ec049e7f0b]
2016-03-28 04:22:20 -05:00
Ben Sander 48773c6d4f Improve debug print messages.
- Remove "call-to-call" for hipStreamCreate and hipEventCreate.
  These now call an internal functions rather than calling through
  hipStreamCreateWithFalgs and hipEventCreateWithFlags.

- Add HIP_INIT_API for more functions so they trace correctly.

- Use stream#DEVICE.STREAMID in debug messages via new specialization in
  tace_helper.


[ROCm/hip commit: 7934cf620d]
2016-03-26 12:35:04 -05:00
Ben Sander 6f88d31a1f Protect _stream_id as well.
- move lockedaccessor
- clean up device class.
- add simple ihipDevice constructor.


[ROCm/hip commit: 395e7eab96]
2016-03-26 11:45:25 -05:00
Ben Sander 141ccad414 Make ihipDevice_t thread-safe.
Move critical data into separate class and protect with LockAccessor
wrapper class.

For device, the streams list is the critical data since it is modified when
streams are created or destroyed.   The streams list is accessed in
several places including when synchronizing across all streams on the
device (ie from the default stream).
Other device data is set once by the device cosntructor and is not critical
so

All functions which acquire the LockAccessor now named with "locked_" prefix.


[ROCm/hip commit: 530ab9434a]
2016-03-26 10:46:20 -05:00
Ben Sander 6553745566 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: 581b884274]
2016-03-25 17:12:13 -05:00
Ben Sander 1531a8c757 describe HIP_PLATFORM
[ROCm/hip commit: 3a7cbe6fca]
2016-03-25 17:11:49 -05:00
Ben Sander 90eb7e1c4e Improve automated platform detection.
If AMD GPU is installed and detected by driver, default
HIP_PLATFORM to hcc.


[ROCm/hip commit: 373251aca0]
2016-03-25 17:08:34 -05:00
Aditya Atluri 56ffa5633e Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
[ROCm/hip commit: b24310b728]
2016-03-25 13:45:46 -05:00
Aditya Atluri db0cd634ba Added test for C + HIP
[ROCm/hip commit: a5628ddfb4]
2016-03-25 13:45:28 -05:00
pensun fa114274ac fix query of memoryClockRate and memoryBusWidth for both NV and HCC path
[ROCm/hip commit: 535de2ecc1]
2016-03-25 09:24:08 -05:00