Change 1:
Adding a regkey LimitConstantBuffersPushed to enable/disable limiting the number of constant buffers
made by: Rishipal S Bhatia
Change 2:
Added a new pattern to the MatchRegisterRegion. In this case we are matching Shuffle(shr(laneid, const)).
made by: Juan1 Rodriguez
Change 3:
Updated the cmake file
made by: Pankaj Mistry
Change 4:
This is the IGC part of fix for issue described in: https://github.com/intel/compute-runtime/issues/21
made by: Pawel Jurek
Change 5:
Added a new pattern to the MatchRegisterRegion. In this case we are matching Shuffle(shr(laneid, const)).
made by: hudson_server
Change 6:
N/A
made by: Manohara Kariganur
Change 7:
made by: Thomas F Raoux
Change 8:
N/A
made by: Manohara Kariganur
Change 9:
Fixing a couple of leaks reported by:
made by: Juan1 Rodriguez
Change 10:
N/A
made by: Manohara Kariganur
Change 11:
This CL refactors IGC code to read maxWorkGroupSize inforamtion from the metadata for compute shaders and choose the appropriate simd mode.
made by: Rishipal S Bhatia
Change 12:
Added a new pattern to the MatchRegisterRegion. In this case we are matching Shuffle(shr(laneid, const)).
made by: Juan1 Rodriguez
Change 13:
The previous perf regression was due to BB layout
made by: Junjie Gu
Change 14:
Hoist loop invariant multiplies outside of loop, fp unsafe optimization.
made by: Peng Guo
Change 15:
Michael Liao investigated performance regression in basemark_julia and found that the issue is related to Clang upgrade. The issue was related to vec3 handling and was fixed in Clang by adding optional -fpreserve-vec3-type option. It was added to our runtime, but wasn't added to CmakeLists responsible for built-in generation.
made by: Pawel Jurek
Change 16:
Changed the way of moving from temporary directory of libraries to the destination. Instead of copying cmake will now make symlinks.
made by: Lukasz Wesierski
Change 17:
BDW platform does not support write to cube texture through HDC.
This workaround consists of the following parts:
1. Adds new field called cubeTo2DArrayWATable to compute compiler output - indices correspond with location indices of textures.
2. Analyses the shader inputs and if it finds cube texture with write or read/write access qualifier, it changes appropriate element in the array cubeTo2DArrayWATable in compute compiler output.
3. Adds flag responsible for switching between old and new workaround, It gives the testing possibility to someone who will be responsible for driver implementation. If driver changes will be done, I'm planning to remove this flag and make code clearer - at this moment old WA is enabled, the new one will be enabled if driver changes will be done.
made by: Andrzej Ratajewski
Change 18:
Reduce the time of split checking for interference graph building
made by: Bu Qi Cheng
Change 19:
Compile time logging
made by: Peng Guo
Change 20:
Back-out of one of previous change.
made by: IGC
Change 21:
Back-out of one of previous change.
made by: IGC
Change 22:
Back-out of one of previous change.
made by: IGC
Change 23:
Spir-V instruction OpCompositeConstruct crashes driver when vector operands are used. Fix is about to extract vector elements before insert them to new composite object.
made by: Lukasz Gotszald
Change 24:
HW swapping is only triggerred by the first simd8 in a simd16, but both sources of two simd8 will swapped.
Inter read suppression is not supported for simd16 instruction
made by: Bu Qi Cheng
Change 25:
Apply rule: "elements within a `Width' cannot cross GRF boundaries"
made by: Bu Qi Cheng
Change 26:
Fix input payload layouts
made by: Jose Santillan
Change 27:
Init tables are already declared in wa_def.h. They are not needed here.
made by: Anupama Chandrasekhar
Change 28:
Automated integration from mainline to DEV_IGC
made by: IGC
Change 29:
If two succs are empty BBs, select one based on some rules, rather than return the first succ all the time.
made by: Junjie Gu
Change 30:
made by: Xiao Lei
Change-Id: I13ae7da8467fcd9214ef24f07893bd979d06b10b
Change 1:
Providing a new AIL to force the a log/mul/exp match into pow. This is work around an issue in SKL, realted to sine/cosine overshooting and return an invalid value. This value will sometimes be negative causing a log operation to return a NaN.
made by: Juan1 Rodriguez
Change 2:
Add 64bit support to OpBitFieldInsert and OpBitFieldExtract SpirV instructions.
made by: Lukasz Gotszald
Change 3:
Do some trivial detection of uniform Alloca which would be converted to uniform vector and reduce the estimated pressure those add
made by: Thomas F Raoux
Change 4:
made by: Thomas F Raoux
Change 5:
made by: hudson_server
Change 6:
Previous pass case was not doing anything as the function doesn't modified the flags
made by: Thomas F Raoux
Change 7:
made by: Thomas F Raoux
Change 8:
Backout of CL738792 due to regression
made by: hudson_server
Change 9:
Refactoring code for enabling subroutine call for other APIs (other than OCL).
1. Rename FunctionInfoMetadata type to be EntryFunctionType/OtherFunctionType, so that they are not ocl-specific.
2. Simplify helper function by using isEntryFunc() only. Get rid of isKernelFunc()/isOCLUserFunc()/isOCLKernelFunc()/isFuncOfType()
made by: Junjie Gu
Change 10:
Add a key for testing purpose
made by: Po-yu Chen
Change 11:
re-enable the feature after fix for mix mode mac
made by: Weiyu Chen
Change 12:
Backout of CL738792 due to regression
made by: Xiao Lei
Change-Id: Ife399d460e8c7cdfcf4eb0feeefe888df8b595bb
Change 1:
Missing description
made by: Junjie Gu
Change 2:
Refactoring code for enabling subroutine call for other APIs (other than OCL).
1. Rename FunctionInfoMetadata type to be EntryFunctionType/OtherFunctionType, so that they are not ocl-specific.
2. Simplify helper function by using isEntryFunc() only. Get rid of isKernelFunc()/isOCLUserFunc()/isOCLKernelFunc()/isFuncOfType()
made by: Junjie Gu
Change 3:
Fixed FRC tests error due to incorrectly copy propogating signed int value with source modifier.
made by: Kai Yu Chen
Change 4:
Hoist loop invariant multiplies outside of loop, fp unsafe optimization.
Resubmit 738243 after fixing functional regressions.
made by: hudson_server
Change 5:
Changed the way IGC receives and stores AIL info from UMD.
Instead store the use the m_uscAilInfo variable from the translationContext itself.
made by: Rishipal S Bhatia
Change 6:
Add a key for testing purpose.
made by: Junjie Gu
Change-Id: I462d7c3a0af433cc51897def105d3d588c9dea20
3d/common/iStdLib/types.h:91:32: error: '-pedantic' is not an option that controls warnings [-Werror=pragmas]
#pragma GCC diagnostic ignored "-pedantic" // warning: ISO C++ prohibits anonymous structs [-pedantic]
Change-Id: I7376783521228493f2d894cf807e7124072e4314
Signed-off-by: Dale Stimson <dale.b.stimson@intel.com>
