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
bf83b949f6
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
2016-03-22 01:17:17 -05:00
ac1eca47f7
Remove kind (aka direction) for copy commands.
...
This is always auto-detected from the src/dest location.
2016-03-21 05:35:36 -05:00
ea352aba6b
suppressed warning in hipFreeHost
2016-03-20 15:31:59 -05:00
f6b38b18b6
Added feature for --default-streams not working tests and hipcc
2016-03-20 08:08:33 -05:00
80d708846a
Implement hipHostFree on HCC path
2016-03-19 23:25:11 -05:00
6984f24d3d
fix nvcc compiler
...
- MallocHost and FreeHost deprecation.
- Change tests to call new hipHost* equivs.
- Add missing StreamSynchronize.
2016-03-19 04:20:15 -05:00
03731020f1
Refactor copy - place common code in resolveMemoryKind.
2016-03-19 22:56:10 -05:00
57365eb7a3
Deprecate hipMallocHost and hipFreeHost.
...
These will print compiler warnings if used, so we can weed them out
before removing.
Also add a default flags args for hipHostAlloc, in the C++ functioin
headers. So you can replace hipMallocHost(&ptr, size( with hipHostAlloc(&ptr, size)
2016-03-19 22:53:59 -05:00
a88c2b1ec9
Refactor waitALlDevices and async mem copy.
...
- move waitAllStreams to device member function.
- create separate stream member function for copyAsync, like copySync.
hipMemcpyAsync now calls the copyAsync.
2016-03-19 05:42:19 -05:00
4c6fd4e7ec
Fix bug: test was allocating host mem instead of device mem.
...
Caused assertion when checking free + allocated should
not exceed total. Bug introduced in hipHostAlloc conversion.
2016-03-19 04:11:39 -05:00
aaa2429feb
Swap in corrected hipHostAlloc (bad merge)
2016-03-19 04:11:08 -05:00
90ad8ddc5d
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
...
Conflicts:
src/hip_hcc.cpp
2016-03-19 03:22:09 -05:00
efc9df8805
disable mt streams tests (for now)
2016-03-19 03:10:31 -05:00
c39b0f9660
Describe HIP env vars
2016-03-19 03:09:57 -05:00
44522eb607
Fix copy and sync bugs. Remove extra sync in default stream.
...
- NULL stream was waiting for itself to be empty before each command.
- Force "blocking" streams to wait for NULL to empty. This was missing
before.
- async copy was disabling itself via trueAsync=false for common cases.
Refactor:
- rename _null_stream to _default_stream.
- move some null sync function to defaultSync, move to dev member func.
2016-03-19 02:44:26 -05:00
5197cf250d
Add beastperiteration and onesize for testing.
...
onesize allows running tests at one specific size.
2016-03-19 02:43:04 -05:00
c5d0813f03
Improve formatting - line up cols
2016-03-18 23:43:04 -05:00
3dc6906855
Print Pinned or Unpinned in result summary
2016-03-18 21:28:29 -05:00
a17e390283
Update CUDA_Runtime_API_functions_supported_by_HIP.md
2016-03-18 11:28:06 -05:00
564d13a0b3
Create CUDA_Runtime_API_functions_supported_by_HIP.md
2016-03-18 11:23:44 -05:00
690486b9eb
Supported --aliged mode. Add results check for H2D and D2H.
2016-03-18 03:09:52 -05:00
e64174f47a
Refactor copy code.
...
-Move staging buffer locks inside the staging buffer code.
-Remove dedicated per-device completion_signal + per-device lock -
instead allocated signal from the per-stream pool. This elimintes
the lock and allows more concurrency.
-remove switch HIP_DISABLE_BIDIR_MEMCPY
2016-03-18 03:02:00 -05:00
3b45e064f9
Refactor staging buffer and sync copies.
...
- refactor staging buffer to operate on hsa* data structures not
hc::accelerator.
- use hsa_memory_allocate to allocate staging buffers rather than
am_alloc.
- Refactor device reset with single member function. Don't reallocate
staging buffers on reset.
- Properly track dependencies based on command type. Add new deps for
H2D and D2D rather than overloading H2D.
2016-03-17 20:09:10 -05:00
1b7cc7d921
Refactor to isolate staging buffer code.
2016-03-17 00:20:56 -05:00
a1879ba59b
Start separaration of staging_buffer.cpp code.
...
Still #include staging_buffer.cpp into hip_hcc.cpp.
Directed tests compile hip_hcc to static library and use the library.
2016-03-16 22:26:49 -05:00
c9d46bdcde
Add aligned alloc
2016-03-16 21:55:57 -05:00
8acb53e160
Checkpoint code cleanup.
...
- Refactor ihipStream in prep for thread-safe implementation.
- Do some work on PinInPlace implementation.
2016-03-16 21:16:29 -05:00
4b96e8c789
changed flag in hipHostRegister
2016-03-16 08:01:53 -05:00
6beed19460
src/ fixed hipHostAllocDefault flags
2016-03-16 07:32:54 -05:00
9b78f0a454
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
2016-03-16 07:17:22 -05:00
7567a6c0ac
Added performance test for memcpy
2016-03-16 07:16:51 -05:00
6baeb08e1c
tests/src [v4] Added feature for partial writes on CPU
2016-03-16 07:04:40 -05:00
9b772c8553
test/src [v3] clean up
2016-03-16 05:30:29 -05:00
8f527d2288
increased iteration size
2016-03-16 05:24:08 -05:00
a60649868d
added cudaHostRegister test
2016-03-16 05:15:03 -05:00
369d01086f
corrected first and second kernel dispatch
2016-03-15 14:22:00 -05:00
a6441c3334
Added single kernel launch to sample
2016-03-15 21:05:15 -05:00
b7bf5830c1
added performance metrics for kernel dispatch
2016-03-15 12:37:24 -05:00
2743a5082f
v2 deprecating hipMallocHost with hipHostAlloc
2016-03-15 13:39:15 -05:00
4d4d592e0c
Deprecating hipMallocHost to hipHostAlloc
2016-03-15 06:30:16 -05:00
bdefb70862
print device config info
2016-03-14 23:02:49 -05:00
15a8e8f8a0
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
...
Conflicts:
src/hip_hcc.cpp
tests/src/CMakeLists.txt
2016-03-14 15:01:26 -05:00
0d05517d0a
enable DB, comments
2016-03-14 14:40:41 -05:00
87c15a3629
Add Bidir copy test and help.
2016-03-14 14:39:23 -05:00
0aab91123b
refactor, add support for speccing xfers in bytes
2016-03-13 09:41:06 -05:00
59f0ef2801
Remove ROCR_V2, assume=1
2016-03-12 04:08:13 -06:00
de4bb0ca0e
Remove USE_AM_TRACKER (assume 1)
2016-03-12 04:04:57 -06:00
ac272932f6
Improve error reporting.
...
use throw with error class.
fix bug when memcpyDefault resolved to D2D copy.
2016-03-12 04:02:04 -06:00
Ben Sander
Aditya Atluri