EPR #410560 - Forum: [169727] Bug? CL_MEM_COPY_HOST_PTR is not thread safe
- Ignore the transfer queue on memory release, since it releases resources after every operation
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#201 edit
[ROCm/clr commit: 9049f11ef4]
EPR #010002 - Change OpenCL version number from 1717 to 1718.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1464 edit
[ROCm/clr commit: 57c517dac7]
EPR #010002 - Change OpenCL version number from 1716 to 1717.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1463 edit
[ROCm/clr commit: 5e0f57fdd0]
EPR #412821 - Default AMD_THREAD_TRACE_ENABLE to true for stg.
So OpenCL sanity will test the OCLThreadTrace test.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#224 edit
[ROCm/clr commit: 7cb94a1247]
EPR #010002 - Change OpenCL version number from 1715 to 1716.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1462 edit
[ROCm/clr commit: db800fd805]
EPR #010002 - Change OpenCL version number from 1714 to 1715.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1461 edit
[ROCm/clr commit: 1329ec0467]
EPR #010002 - Change OpenCL version number from 1713 to 1714.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1460 edit
[ROCm/clr commit: 38bbacc397]
EPR #010002 - Change OpenCL version number from 1712 to 1713.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1459 edit
[ROCm/clr commit: bc142e9ecb]
EPR #010002 - Change OpenCL version number from 1711 to 1712.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1458 edit
[ROCm/clr commit: 4dcfbf27d4]
EPR #010002 - Change OpenCL version number from 1710 to 1711.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1457 edit
[ROCm/clr commit: 681416b56d]
EPR #010002 - Change OpenCL version number from 1709 to 1710.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1456 edit
[ROCm/clr commit: d1bf1dbf61]
EPR #010002 - Change OpenCL version number from 1708 to 1709.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1455 edit
[ROCm/clr commit: dc57153e6f]
EPR #010002 - Change OpenCL version number from 1707 to 1708.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1454 edit
[ROCm/clr commit: 187a905974]
EPR #010002 - Change OpenCL version number from 1706 to 1707.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1453 edit
[ROCm/clr commit: 8fef9d0995]
EPR #010002 - Change OpenCL version number from 1705 to 1706.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1452 edit
[ROCm/clr commit: 01cfbfc12c]
EPR #010002 - Change OpenCL version number from 1704 to 1705.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1451 edit
[ROCm/clr commit: 9313a79416]
EPR #010002 - Change OpenCL version number from 1703 to 1704.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1450 edit
[ROCm/clr commit: a6cf2b4c75]
EPR #010002 - Change OpenCL version number from 1702 to 1703.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1449 edit
[ROCm/clr commit: b8b34603f1]
EPR #410797 - Specific OCL kernel is 5x slower on Hawaii than on Nvidia K40 GPU when tested under Linux.
- The logic for local workgroup size search was prioritizing ALU utilization, but with multidemensional launches X dimension could affect address calculation and cacheline utlization more than others. Add cacheline size into the consideration.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#270 edit
[ROCm/clr commit: 674da4560d]
EPR #411189 - Fix windows handling of SIGFPE. We cannot check worker thread during creation, because the constructor has not yet been called.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/os/os_win32.cpp#43 edit
[ROCm/clr commit: 5a2d6ed3c7]
EPR #411058 - [CQE OCL][Lnx][QR][CZ]MultiDevice_Context fails in 2.0 conformance wimpyfull due to CL# 1101352
- The detection of different map types is overcomplicated with possibility of multiple maps and multithreading environment. Thus keep USWC indirect map optimization based on the allocation flags.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.cpp#114 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.hpp#46 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#342 edit
[ROCm/clr commit: 593d1e3b8d]
EPR #010002 - Change OpenCL version number from 1701 to 1702.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1448 edit
[ROCm/clr commit: c722a0a2da]
EPR #010002 - Change OpenCL version number from 1700 to 1701.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1447 edit
[ROCm/clr commit: 68108a505c]
EPR #405889 - Added option to set VGPR/SGPR/LDS usage in ISA to certain value greater than actual usage for debugging purpose. If the given value is smaller than actual value, this option has no effect.
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/scwrapper/SI/scCompileSI.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/scwrapper/scHWShaderInfo.h#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/OPTIONS.def#121 edit
[ROCm/clr commit: 9f760b7bf0]
EPR #010002 - Change OpenCL version number from 1699 to 1700.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1446 edit
[ROCm/clr commit: ed3642807b]
EPR #010002 - Change OpenCL version number from 1698 to 1699.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1445 edit
[ROCm/clr commit: f4addd58c9]
EPR #410824 - [CQE OCL][CZ][S/G][QR] Two Bolt sample failing on CPU; Faulty CL: 1101352
- The test performs double maps with different map flags. Optimization could choose different map schemes for each call and memory coherency could be broken. Add extra conditions to detect multiple maps and use the same path as the first map.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.hpp#45 edit
[ROCm/clr commit: a1202e54be]
EPR #010002 - Change OpenCL version number from 1697 to 1698.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1444 edit
[ROCm/clr commit: 3444e16d99]
EPR #010002 - Change OpenCL version number from 1696 to 1697.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1443 edit
[ROCm/clr commit: 2d58fc417b]
EPR #410736 - [CQE OCL][ISV][QR][G] FFMPEG app generating corrupted video output; Faulty CL:1101352
- Add detection for AHP allocation.
FFmpeg uses AHP allocations with CL_MAP_READ flag, but actually performs CPU write into the buffer. With indirect map runtime executes useless transfer on map and doesn't write updated memory on unmap, because a wrong flag sent by the app.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.cpp#113 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.hpp#44 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#341 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/perf/TestList.cpp#40 edit
[ROCm/clr commit: f9f5df731e]
EPR #010002 - Change OpenCL version number from 1695 to 1696.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1442 edit
[ROCm/clr commit: 750e1bf9bd]
EPR #010002 - Change OpenCL version number from 1694 to 1695.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1441 edit
[ROCm/clr commit: 6824541acd]
EPR #010002 - Change OpenCL version number from 1693 to 1694.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1440 edit
[ROCm/clr commit: ba8e6fefbe]
EPR #397491 - Replace "switch" with "if" so that new ASIC id doesn't need to be added.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#103 edit
[ROCm/clr commit: afe1835f56]
EPR #403782 - IOMMU2/SVM
- For finegrainsystem, the app can pass a malloced pointer directly to the kernel. Copy pointer directly to the aqlArgBuf without exiting.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/6378/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#269 edit
[ROCm/clr commit: 2ba0f2a112]