9ee70fca8a
Merge pull request #672 from iotamudelta/fp16_fix
...
Only LLVM6 and higher contain the necessary intrinsics.
2018-09-18 08:43:33 +05:30
32787fa1fc
Merge pull request #674 from mangupta/fix_dtests_on_nvcc
...
[dtests] Fix hipTestClock, hipTestNew, hipTestGlobalVariable, hipSimpleAtomicsTest & hipTestIncludeMath tests on nvcc path
2018-09-18 07:50:52 +05:30
5cf281071d
Merge pull request #677 from yxsamliu/fix-launch-decay
...
Fix hipLaunchKernelGGL for hip-clang
2018-09-18 07:50:37 +05:30
d28ce807c7
Merge pull request #676 from VincentSC/patch-1
...
Update install.sh
2018-09-18 07:50:28 +05:30
47bd84974b
Merge pull request #678 from yxsamliu/fix-memory
...
Disable device code for gcc in hip_memory.h
2018-09-18 07:50:18 +05:30
cdfd82f1de
Disable device code for gcc in hip_memory.h
...
These device code should only be seen by HCC or hip-clang. They causd build failure
for HIP-VDI runtime and should be disabled for gcc.
2018-09-17 16:50:42 -04:00
fc228c7ea6
Fix hipLaunchKernelGGL for hip-clang
...
Do not decay function pointer type of the kernel argument passed to hipLaunchKernelGGL
and hipLaunchKernel, otherwise some type information is lost which may cause
type inference failure for the template.
This issue caused compilation error of FeatureLPPooling in Caffe2/PyTorch and this patch
fixes that.
2018-09-17 11:20:41 -04:00
30acc99e13
Update install.sh
...
'rename' added as a Linux prerequisite.
2018-09-17 13:25:12 +02:00
cca2c5afc8
[dests] Fix hipTestClock, hipTestNew & hipTestGlobalVariable tests for nvcc
...
nvcc does not support global kernels in struct/class
Change-Id: I2d7297e0c3725564215e20dbdd31c0bb8d7a07de
2018-09-17 15:32:05 +05:30
94a0589eb5
[dtests] Fix deviceLib/hipSimpleAtomicsTest for nvcc
...
Change-Id: I23cbea2820d41da6f6a1bcab4bc3b59ac21799dd
2018-09-17 15:26:45 +05:30
cef5261fa9
Add mappings for __clock* in nvcc_detail/hip_runtime.h
...
Change-Id: Ibcecf52f3e69298268d921efc036090544fa0ed0
2018-09-17 15:23:30 +05:30
0b211bb429
[dtests] Fix deviceLib/hipTestIncludeMath on nvcc path
...
Change-Id: Ifb121886bec6c1134e98bd194ff1713f28454d33
2018-09-17 15:15:49 +05:30
30b1494c3d
Merge pull request #606 from ROCm-Developer-Tools/add-test-global-var
...
Add HIP directed test hipTestGlobalVariable.cpp
2018-09-17 11:11:51 +05:30
319d6dce5e
Merge pull request #598 from ROCm-Developer-Tools/support-malloc
...
Support device-side malloc/free for hip-clang
2018-09-17 11:11:36 +05:30
66f863d1f3
Merge branch 'master' into support-malloc
2018-09-17 10:17:25 +05:30
48cc4f0d9e
Merge pull request #639 from ROCm-Developer-Tools/skudchad-hip
...
Check for hipEnvVar at the same level if directed_tests location fails
2018-09-16 18:31:37 +05:30
9b2107749c
Revert changes to runtime/stream/hipStreamSync2
2018-09-15 13:23:38 +05:30
cb348421d7
Merge pull request #650 from ROCm-Developer-Tools/hip-clang-new
...
Support placement new in hip-clang
2018-09-15 11:21:01 +05:30
233ac1e0f0
Merge pull request #636 from ROCm-Developer-Tools/db-fatbin
...
Add HIP_DB=fatbin for debugging fat binary issues
2018-09-14 13:21:58 +05:30
d6ce39c1b7
Merge pull request #637 from ROCm-Developer-Tools/add-pthread
...
Let hipcc link -lpthread -lm by default
2018-09-14 13:21:47 +05:30
8fe4e22b19
Merge pull request #665 from aaronenyeshi/fix-min-funcs
...
Use templates for min to prevent ambiguity
2018-09-14 13:21:38 +05:30
93a07ae6cb
Merge pull request #642 from ROCm-Developer-Tools/handle-obj
...
Let hipcc handle obj files in linker response file for hip-clang
2018-09-14 08:59:53 +05:30
87bf9aa9d1
Merge pull request #658 from phani544/hipClangFrndClass
...
[HIP-Clang]Add friend class/function test
2018-09-14 08:59:40 +05:30
6b811ca6d1
Fix Tensorflow ambiguous min issue
2018-09-13 23:16:20 +00:00
cf12a9c049
Only LLVM6 and higher contain the necessary intrinsics.
2018-09-13 13:55:43 -05:00
5cb819b34e
Merge pull request #633 from aaronenyeshi/hip-clang-remove-am
...
Remove few hcc specific cmake for hip-clang
2018-09-13 10:20:12 +05:30
aed5ad31ba
Merge pull request #669 from ROCm-Developer-Tools/feature_automatic_cast
...
Remove potential for mismatch between runtime passed actuals and defined formals
2018-09-13 07:54:22 +05:30
c44906011d
Merge pull request #670 from gargrahul/remove_adipose_launchkernelhcc
...
Remove adipose extn from launchKernelHcc sample
2018-09-13 07:54:11 +05:30
411e53a665
Merge pull request #661 from yxsamliu/add-empty-printf
...
Add empty printf for hip-clang
2018-09-13 07:54:03 +05:30
48f3d77185
Merge pull request #648 from ROCm-Developer-Tools/yxsamliu-patch-2
...
Document kernel launching for hip-clang
2018-09-13 07:53:50 +05:30
894cbdd749
Avoid AMP-retrict call to CPU-restrict
2018-09-12 14:54:31 +00:00
fb706902cc
Remove adipose extn from launchKernelHcc sample
2018-09-12 16:41:24 +05:30
cdfea3ef7b
Remove potential for mismatch between runtime passed actuals and defined formals.
2018-09-12 10:30:48 +01:00
8249cf037b
Merge pull request #664 from lcskrishna/master
...
added __host__ to float2half and half2float functions.
2018-09-12 14:50:01 +05:30
133d665a88
Merge pull request #663 from yxsamliu/fix-launch
...
Use template for hipLaunchKernelGGL for hip-clang
2018-09-12 14:49:38 +05:30
fefb2b2e68
Merge pull request #667 from carlushuang/longlong_as_double_fix
...
fix __longlong_as_double() problem, return the double value
2018-09-12 12:53:57 +05:30
e63205fad8
Merge pull request #666 from ROCm-Developer-Tools/mangupta-patch-2
...
[ci] Disable hipVectorTypes* tests in CI
2018-09-12 12:52:15 +05:30
d577f27d1a
fix __longlong_as_double() problem, return the double value
...
previous version return a long long valus *as* double, hence we may get the wrong result.
this also affect atomicAdd(double * ...), which use long long pointer to mimic double pointer.
Signed-off-by: carlushuang <carlus.huang@amd.com >
2018-09-12 13:25:00 +08:00
cb6cf6584e
[ci] Disable hipVectorTypes* tests in CI
...
Disable directed_tests/deviceLib/hipVectorTypes.tst & directed_tests/deviceLib/hipVectorTypesDevice.tst in CI due to HCC regressions. Once HCC fixes are in, the tests can be re-enabled in CI.
2018-09-12 10:32:15 +05:30
ffd89dde9c
Avoid host min func conflict with gcc min
2018-09-11 18:48:31 +00:00
0121ec13aa
Use templates for min to prevent ambiguity
2018-09-11 18:21:54 +00:00
9e9a93e10a
Use template for hipLaunchKernelGGL for hip-clang
2018-09-07 16:20:00 -04:00
3e1833ca52
Add empty printf for hip-clang
2018-09-07 16:15:08 -04:00
2984c020b8
added host for float2half and hlaf2float
2018-09-06 15:02:52 -07:00
a8bc26344f
[HIP-Clang]Add friend class/function test
2018-09-05 11:48:49 +05:30
4f17b4877e
Let hipcc link -lpthread -lm by default
2018-09-04 17:11:47 -04:00
1587b18a91
Let hipcc handle obj files in linker response file for hip-clang
...
If obj files in linker response file contains device code, pass them to hip-clang, otherwise keep them in the linker
response file.
2018-09-04 16:57:55 -04:00
1bb28375bc
Document kernel launching for hip-clang
2018-09-04 16:56:53 -04:00
338eaefa84
Support placement new in hip-clang
2018-09-04 16:53:46 -04:00
52b8879f12
Merge pull request #654 from ROCm-Developer-Tools/fix-force-inline
...
__forceinline__ needs inline and always_inline
2018-09-03 16:35:34 +05:30
Maneesh Gupta
Yaxun Sam Liu
VincentSC
Aaron Enye Shi
Johannes M Dieterich
Rahul Garg
Alex Voicu
carlushuang
lcskrishna
fpadmin