German Andryeyev
597bf599ad
SWDEV-193956 - [hipclang-vdi-rocm][perf]
...
~45% to 50% of Performance drop on rocBLAS_int8 test
Enable cudaSetDeviceFlags() api call. Use active wait by default
for all devices.
Change-Id: Ifc2ebe3dd9b0aa3fdbfbc9cb5c2cd8b3b726124f
[ROCm/clr commit: b93d997fb7 ]
2020-03-02 18:35:56 -05:00
Vladislav Sytchenko
e0ac3b427d
Report the HW requirments for pitch alignment
...
Change-Id: Iaaa9d597dff57cfad5d07d931f881aba1a5f98f1
[ROCm/clr commit: 8be685e7b9 ]
2020-02-21 11:09:47 -05:00
Christophe Paquot
dad62d78c0
Introducing hip::Device which wraps around amd::Context and deviceId
...
Change-Id: Ie35a6edb65c001b35eb9f5d2af26e765dc41c00e
[ROCm/clr commit: b4ad4262cc ]
2020-02-18 17:18:56 -05:00
Laurent Morichetti
3765569608
Update copyright info for VDI files
...
Change-Id: Ib160fbf89ec89a5895321f73402a33b4d344a68f
[ROCm/clr commit: 5b098e68b6 ]
2020-02-04 08:47:10 -08:00
Laurent Morichetti
bb38362f74
Merge HIP/VDI branch 'amd-staging' into lmoriche/amd-master-next
...
Change-Id: Iabaab4e72815ba483a1330ec6a1130f2b86676f0
[ROCm/clr commit: 6f3e18a764 ]
2020-01-29 15:02:13 -08:00