EPR #410989 - Set globalScratchBuf_ to NULL after it is deleted.
The issue is that scratch buffer will be destroyed again when the transfer queue is destroyed.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#492 edit
[ROCm/clr commit: 6ea7225039]
ECR #333753 - Compiler Lib/ORCA RT/Performance: BRIG in BIF is not needed anymore for finalizing & executing ISA (except cases with program scope global variables).
[Description] The feature is intended to minimize the binary size for execution.
This is half-hearted solution: If -fno-bin-cg is set, then after ISA finalization all BRIG sections are removed from the binary, but if there are program scope global variables in code, the option is ignored and all BRIG sections retain in binary for further globals allocation & initialization. The complete solution awaits Code Objects implementation.
+ Additionally change fixes Bug 10478.
+ Recompilation steps determination is changed in RT.
+ symBRIGLoaderMap is added to bif_section_labels.
+ RT_CONTAINS_LOADER_MAP is added for aclQueryInfo in order to check symBRIGLoaderMap existance in binary.
+ complib tests are added on -fbin-cg/-fno-bin-cg.
+ ocltst -t complib -M CLEnumCheck is updated.
[Side effects] performance improvement, memory consumption reduction
[TODO] Do the same on .hsa bits.
[Testing] pre check-in, make smoke, complib, ocltst: complib, compiler, runtime, binary
[Reviewer] German Andryeyev
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.cpp#59 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/brig_loader.cpp#17 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/hsail_be.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/hsail_be.hpp#12 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/scwrapper/scClientAPI.cpp#21 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclEnums.h#16 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/bif_section_labels.hpp#19 edit
... //depot/stg/opencl/drivers/opencl/compiler/loader/libloader/loader.cpp#12 edit
... //depot/stg/opencl/drivers/opencl/compiler/tools/aoc2/aoc2.cpp#64 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#188 edit
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fbin-cg-g/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fbin-cg-g_globals/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fbin-cg/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fbin-cg_globals/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fno-bin-cg-g/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fno-bin-cg-g_globals/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fno-bin-cg/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fno-bin-cg_globals/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/tlst/complib.tlst#5 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/complib/CLEnumCheck.cpp#40 edit
[ROCm/clr commit: 84508bb5a4]
EPR #010002 - Change OpenCL version number from 1723 to 1724.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1470 edit
[ROCm/clr commit: 9276e5b992]
EPR #010002 - Change OpenCL version number from 1722 to 1723.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1469 edit
[ROCm/clr commit: 08f0e15bca]
EPR #010002 - Change OpenCL version number from 1721 to 1722.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1468 edit
[ROCm/clr commit: c51f296496]
EPR #010002 - Change OpenCL version number from 1720 to 1721.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1467 edit
[ROCm/clr commit: 3eb6dee213]
EPR #010002 - Change OpenCL version number from 1719 to 1720.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1466 edit
[ROCm/clr commit: cc54e51cfb]
EPR #411675 - Disable the code of writing 0 for the buffer paging by VidMM if asic is apu.
On Kaveri, benchmark "photo editing" of PCMarks takes longer time
Not sure how PCMarks measures it.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#202 edit
[ROCm/clr commit: fe8a3fc53e]
ECR #333753 - Partial fix for Bug 10478 "Fix -fno-bin-llvmir/-fno-bin-hsail options"
If option -fno-bin-llvmi is set, .llvmir section is deleted from BIF on CG phase instead of FE. Both HSA & AMDIL are affected.
[Fixed] -fno-bin-llvm option causes clBuildProgram fail with error -11.
Took place only if compiled from OpenCL
[TODO] If possible -fno-bin-hsail should avoid putting HSAIL binary (BRIG) into BIF.
[Tests] pre check-in, make smoke, complib
[Reviewers] Brian Sumner, Nikolay Haustov
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/frontend.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/frontend_clang.cpp#17 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.cpp#58 edit
... //depot/stg/opencl/drivers/opencl/compiler/tools/aoc2/aoc2.cpp#63 edit
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fbin-llvmir/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/complib/options/-fno-bin-llvmir/HelloWorld_Kernel_cl.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/tlst/complib.tlst#3 edit
[ROCm/clr commit: 770a084e70]
EPR #010002 - Change OpenCL version number from 1718 to 1719.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1465 edit
[ROCm/clr commit: c2128824a2]
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]