52ac414b40
Use HCC get_is_pool, add USE_PEER_TO_PEER level 2, 3.
2016-04-11 07:58:58 -05:00
97772d6363
For P2P, use the peer list when allocating Device memory or pinned host.
...
Each new allocation is automatically mapped into the address space of
all enabled peers.
2016-04-11 07:58:58 -05:00
e2d19d7f7a
P2P checkpoint.
...
Maintain enabled peer tables for each device.
2016-04-11 07:58:58 -05:00
4400875dda
Checkpoint initial peer2peer implementation.
2016-04-11 07:58:58 -05:00
42df534354
added C guard to hip_runtime.h
2016-04-11 13:01:02 -05:00
b8fed74f62
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
2016-04-07 04:57:54 -05:00
c006359510
C proofing hip
2016-04-07 04:57:31 -05:00
39f27984a8
Added feature for cross-compilation and seperated hcc api from hip api
2016-04-06 14:18:51 -05:00
c2d04ba59c
added device math functions
2016-03-31 12:29:19 -05:00
48b8b426d5
moved cpp specific device code from headers to source
2016-03-31 04:45:00 -05:00
c4d93cf3db
C guarding the apis
2016-03-30 06:08:50 -05:00
e476d4e8f0
Moved flag to hip_runtime.h
2016-03-30 03:32:39 -05:00
00bf37d28d
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
2016-03-29 11:18:09 -05:00
e7b15a53da
Inline some new string functions.
2016-03-29 17:28:27 -05:00
e22925be22
Add runtime switch to control HIP_ATP_MARKER
...
Only generate the function strings if requested at
compile-time && runtime.
2016-03-29 17:27:30 -05:00
03c0fcbfec
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
2016-03-29 14:43:35 -05:00
3b3db60c25
Calling intrinsics from global kernel
2016-03-29 11:17:55 -05:00
ba114a238f
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
...
Conflicts:
include/hcc_detail/trace_helper.h
2016-03-29 05:56:03 -05:00
73ecbf5c95
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
2016-03-29 02:28:20 -05:00
8e437d0565
Not using classes inside headers
2016-03-29 02:27:51 -05:00
1b2ab173c1
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).
2016-03-28 21:41:47 -05:00
3aa542e21b
turn off ONE_OBJECT_FILE since we are building a static library
2016-03-28 12:56:15 -05:00
6cab7862ae
Stream thread-safe checkpoint.
...
Moving data structures to critical / protected section.
2016-03-28 09:46:40 -05:00
5afa5d23fc
add inline keyword to all the template functions
2016-03-28 09:18:38 -05:00
4f8786c66a
fix ihipLogStatus so status arg only evaluated once
2016-03-28 05:23:53 -05:00
ecd56e1400
Stream thread-safe checkpoint.
2016-03-28 04:22:20 -05:00
82f57ca610
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.
2016-03-26 12:35:04 -05:00
c47b5b04ef
Protect _stream_id as well.
...
- move lockedaccessor
- clean up device class.
- add simple ihipDevice constructor.
2016-03-26 11:45:25 -05:00
4dd77c6612
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.
2016-03-26 10:46:20 -05:00
a8ae62d399
fix query of memoryClockRate and memoryBusWidth for both NV and HCC path
2016-03-25 09:24:08 -05:00
ac57672eaa
Fix release notes and minimum required hcc workweek check
2016-03-25 16:08:00 +05:30
2dacc3e161
Added canMapMemory feature to device properties
2016-03-24 07:33:24 -05:00
eea49cb66b
added CR and hipsetdeviceflags func
2016-03-24 07:04:01 -05:00
1c55019322
Split files based on functionality and changed cmake file
2016-03-24 04:57:30 -05:00
0e92a64b95
CMake improvements.
...
- Directed tests build hip_hcc as subdir.
- Support HCC_HOME env var to control which HCC to use for build
hip_hcc.
2016-03-24 10:16:35 -05:00
c1ad70ad4b
moved variables to headers
2016-03-23 12:59:52 -05:00
29119bd3d4
reverted back to old infra with cmake added
2016-03-23 11:13:02 -05:00
64c4c70e4f
WIP added modular feature for device apis
2016-03-23 07:54:01 -05:00
24496b1c38
Merge pull request #18 from AMDComputeLibraries/grid_launch_index
...
Grid launch index fix
2016-03-23 11:26:28 -05:00
3ca91cf327
Update docs:
...
- Some comments in hip_hcc.cpp
- document hipHostRegister* flags.
- expand docs on hipHostRegister/Unregister. Use "register" rather than
"pin" to describe action these take.
- change required CUDA version to 6 (require unified memory)
- remake doxygen.
2016-03-23 23:11:15 -05:00
1313f1fb77
add compiler version guard to the grid launch fix
2016-03-23 11:24:37 -05:00
671128abb0
fix builtins mapping for IDs and Dims
2016-03-23 11:08:28 -05:00
8954e4fb26
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
...
Conflicts:
src/hip_hcc.cpp
2016-03-23 03:22:09 -05:00
fa8deac1ad
Improve trace API
...
- Validate compile-time disables.
- Add README.md section explain how to install/use CodeXL tracing
- Add code docs on trace_helper.h
- fix color on hipLaunchKernel to green.
2016-03-23 02:57:52 -05:00
723327cd0f
Describe how to file an issue
2016-03-23 01:15:05 -05:00
2d0fade1f7
hipHostRegister and hipHostMalloc refactor.
...
Note hipHostMalloc (not hipHostAlloc or hipMallocHost).
- the hipHost* is used for all HIP APIs dealing with Host memory.
(including hipHostMalloc, hipHostFree, hipHostRegister,
hipHostUnregister, hipHostGetFlags, hipHostGetDevicePointer).
- hipMallocHost is consistent with "hipMalloc" for allocating device
memory. Enumerations hipHostMalloc* also used as optional
flags parm to hipHostMalloc.
2016-03-22 02:30:10 -05:00
8af8ee2476
Revert "Revert "fixed memory free apis""
...
This reverts commit 1fa4d0d4b9
2016-03-21 10:40:42 -05:00
bde1e6182d
Revert "Revert "fix nvcc for hipHostMalloc* flags.""
...
This reverts commit 83fee90e83
2016-03-21 10:39:49 -05:00
83fee90e83
Revert "fix nvcc for hipHostMalloc* flags."
...
This reverts commit d495ffb1d3
2016-03-21 10:36:14 -05:00
1fa4d0d4b9
Revert "fixed memory free apis"
...
This reverts commit 71a6b5cb6c
2016-03-21 10:36:11 -05:00
Ben Sander
Aditya Atluri
scchan
pensun
Maneesh Gupta
Aditya Atluri