igc-1.0.5064

Fixed Issues / Improvements

• Multiple refactor changes in preparation of LLVM upgrade to version 11.
• Added shader dumping capabilities to VectorCompiler.
• VectorCompiler now uses DebufInfo library.
• Refactored debug information.
• Fixes for compilation for OpenCL 3.0.
• Remove alwaysinline attributes for call instructions if -cl-opt-disable is present.
• Avoid FP64 emulation related code if kernel doesn't use FP64 at all.
• Instruction splitting is now handled by vISA.
• Enable splitting of instructions with indirect addressing.
• Update GED version to 0.68.
• Improvements to the legalizaton of shuffle-vector.
• Removed LShr and AShr operands truncation.
• Restricting spill space compression intra-iteration only in interest of compile time and memory usage.
• Removed the EnableOCLNoInlineAttr flag, NoInline should be honored by default.
• Multiple other improvements and minor changes throughout the project.

Dependencies revisions

• intel/llvm-patches@c4a0345
• intel/opencl-clang@6a9cd2c
• KhronosGroup/SPIRV-LLVM-Translator@424e375 (for opencl-clang)
• intel/vc-intrinsics@8300678
• KhronosGroup/SPIRV-LLVM-Translator@e8a52ab (for VectorCompiler)
• llvm/llvm-project@llvmorg-10.0.0

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4944

Fixed Issues / Improvements

• Multiple refactor changes in preparation of LLVM upgrade to version 11.
• Vector backend improvements:
  • clearer reports about unsupported types,
  • introduced i64 emulation pass,
  • support for -ftime-report,
  • support for genx_addc and genx_subb intrinsics.
• Added support for OpConstFunctionPointerINTEL, 1024-bit constants in SPIRVReader.
• Added patches for SPIRV-LLVM-Translator based on LLVM9.
• Added support for experimental SYCL unmasked call feature.
• Added option to force thread group size.
• Added fallback path when ZEBinary is enabled by -allow-zebin.
• Updated CMFE interface.
• Relaxed some checks to allow a subset of i64 operations for targets without native i64 support.
• Fixed translation of non 32/64-bit constants.
• Fixed processing of GEP instruction when the index is a vector.
• Fixed buildbreak with VectorCompiler switched off.
• Removed unused IGA files, updated IGA.
• Many minor optimization and code improvements throughout whole project.

Dependencies revisions

• intel/llvm-patches@c4a0345
• intel/opencl-clang@6a9cd2c
• KhronosGroup/SPIRV-LLVM-Translator@424e375 (for opencl-clang)
• intel/vc-intrinsics@55124bb
• KhronosGroup/SPIRV-LLVM-Translator@e8a52ab (for VectorCompiler)
• llvm/llvm-project@llvmorg-10.0.0

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4879

Fixed Issues / Improvements

• SWSB sync instruction optimization
• Increase large basic block size to calculate register pressure.
• Support for emitting GenISA_simdShuffleDown in missing execution size (SIMD32)
• Decode DIExpression operation in SPIRV reader.
• Support emulation of general call and return for i64 type.
• Enable accumulator use for ror/rol.
• Minor fixes and improvements.

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4756

Fixed Issues / Improvements

• Update EOTRenderTarget() to use RTW instruction instead of a raw send.
• Add WA to set noMask for all sampler.
• Type of for statement iterator changed from unsigned int to uint64_t to prevent hangs.
• Initial support for source/line debug information in VectorCompiler backend.
• Fix a bug for A64 block store with byte source operand.
• Fix number of elements to use in G4_Declare creation in remat.
• Make IGC emit DW_AT_abstract_origin for inlined DW_TAG_lexical_block constructs.
• Add a check to avoid invalid dereference.
• Incorrect code generation for xor fix.
• Adding a regkey to override product for debugging.
• Create dummy kernel to attach symbol table and indirectly-called functions.
• Move bfrev pattern from GenSpecificPattern to CustomSafeOptPass.
• Adding attribute for selective stack calls.
• Disable rematerialzation of intrinsic.split instruction.
• Assign DebugLoc to pre-defined variables. Skip sinking of allocas when -cl-opt-disable is applied to keep .debug_ranges clean for inlined functions.
• Fixes for OCL 3.0 feature macro usage.
• Fix CISA offsets before splice operation in spill insertion.
• Update EOTRenderTarget() to use RTW instruction instead of a raw send.
• Fix regression in promotion of dynamic buffers to registers.
• Allow enabling some features in Release mode using environment variables.
• ZEBianry: support .spv and .gtpin_info section.
• Add pass to classify move types.
• Do not copy R0 when creating the header for bindless sampler message.
• Eliminate select+phi redundancy in SIMD CF
• Enable explicit variable split.
• Fix some bugs in ZEBinary - Fixed ELF flag - Rename .data.global_const to .data.const - Remove local_id info if not used
• Remove unncessary add for the common special case of add.pair with zero high32-bit values.
• Add backend configuration pass for VC.
• Merge instructions for 64bit emulation.
• Add pass to Split Indirect EE to sel to avoid VxH mov.
• Add dependency for EstimateFunctionSize.
• Emit single copy of pre-defined variables when -cl-kernel-debug-enable is passed.
• Inlining algorithm for controling Kernel Total Size.
• Forward pointer support in SPIRV Reader.
• Run earlyCSE after GEPLowering to optout some instrcutions introduced by GEPLowering.
• Switching from -runtime to -binary-format option -binary-format=ze for ZEBinary output.
• Stitch indirectly-called functions to the binary on VC side.
• Starting from tgllp mid-thread preemption is no longer supported. EnablePreemption value should be set to false for these new platforms.

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4594

Fixed Issues / Improvements

• DWARF SIMD location expressions support cont.
• Emit debug info for lower and upper 16 channels for SIMD32
• Add an opt for dp4 with identity matrix
• GRF register info available in dump
• Minor fixes and improvements.

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4560

Fixed Issues / Improvements

• Removed redundant constant folding in HW legalization checks.
• Added ABI validation for CMFE.
• Added flushing L3 for device or cross-device memory fence on global memory.
• Added missing help text for alias options in VC.
• Moved IntrinsicGenISA.gen to build Config folder and added proper dependency requirement.
• Fixed VertexShaderLowering incorrectly clearing out Vertex Header when it is actually used.
• Fixed in LRA to ensure startGRFReg is less than number of GRFs available for allocation to linear scan.
• Fixes for vISA assembly.
• Fixed vector alloca type in TransformPrivMem for function pointers cases.
• Fixed and further implementation of IGC_ASSERT.
• Fixed args passed to register for non-uniform function calls.
• Disabled SIMD32 slicing when -cl-opt-disable is passed instead of -g.
• Disabled legacy mad to mac optimization.
• Implemented SIMD compile info for OCL shaders.
• Improved alloca uniform analysis.
• Allowing DisableAddingAlwaysAttribute flag in release mode.
• Switched to accessing GenXSubtarget through TargetPassConfig.
• Minor refactoring and deprecated code removal.

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4521

Fixed Issues / Improvements

• Fix bugs in image/sampler tracking to properly track argument when compiling with -cl-opt-disable
• Move pass to erase redundant movs after other optimizations are done.
• Skip simd32 compilation for per-pixel dispatch with x16 samples.
• Revert new-reg-per-function behavior in VC RA
• Add new Relocation Type R_PER_THREAD_PAYLOAD_OFFSET_32 Also refactor vISA::RelocationEntry create API
• Moving IntrinsicGenISA.gen to build Config folder and adding proper dependency requirement
• Switch to using LLVMTargetMachine in VC. Initialized GenX pass in BackendPlugin.
• Add check for fp64 and i64 copy move if platform does not support 64b types.
• Program the correct response length for spill of a scalar variable used as send dst.
• Enable FP64 accumulator as mul instruction source.
• Add TGL emulation functions for DP and SP
• DWARF debugger location expressions
• Emit variable location off privateBase
• additional include guards to avoid re-defintion conflict of LARGE_INTEGER type
• Uniform analysis tuning for performance.
• For stack calls do not adjust the spill size by global scratch offset
• Relocations and symbols support in L0 binary in VC
• Update register numbering for debug info.
• Try to avoid bank conflict for Gen12 when scheduling
• Fix some excessive mov instructions emitted by VectorCompiler.
• Avoid unncessary llvm metadata regenerations to optimize compilation time

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4479

Fixed Issues / Improvements

• Fail compilation with error message instead of crash if we can't find sampler argument or inline/global sampler.
• DWARF debugger location expressions fixes.
• Remove redundant LICM pass.
• Enable timestats through regkey.
• extend the MarkReadOnlyPass to mark loads with constant address space with invariant.load.
• Adding metadata for computedDepthMode.
• Enable vISA instruction splitting pass.
• Open-sourcing CM FE related parts of driver.
• Fix system LLVM handling in VC.
• update integer splitter api in VectorCompiler.
• Improve lowering of ord/unord fcmp.
• Emask calculation correcting by remove the write enable and using right data types.
• Basic block where flow control partially joins should also be treated as divergent.
• Limit total thread payload size to 96 GRFs.
• Tighten up vISA assembly syntax: do not allow missing regions for general operands, do not allow two offsets for address operands.
• Fixed operations with overflow.
• Prevent tracking of images and samplers from falling into infinite loop.
• Fix lowpc/highpc for subroutines in debug info.
• Make Dst operand's subreg offset immutable.
• Get rid of unnecessary MOVS.
• Check for undefined predicate variables when parsing vISA assembly.
• Removing the dst/src overlap checking after augmentation.
• ZEBinary: add kernel symbol.
• Fix TPM's replaceGatherPrivate.
• Add ZEAutoTool.
• Report parser error for vISA inline assembly in releaseInternal build.
• ZEBinaryBuilder: Fix packed_local_ids size to 6 instead of 12.
• DWARF debugger location expressions fixes.
• Avoid multiple metadata regenerating in AggregateArguments pass.
• Refactor for stack call functions. Combine code for caller/callee stack load/store.
• Fix shuffleVector lowering in legalization pass.

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4427

Fixed Issues / Improvements

• Handle 16-byte alignment correct for trivial and local RA.
• Introduce ExtraOCLOptions debug key.
• Improve URB merging.
• Initial support of L0 binary in cmc.
• Add pattern match to emit integer trunc instruction with saturation.
• Update of static bank conflict checking.
• Minor fixes and improvements.

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.

igc-1.0.4361

Fixed Issues / Improvements

• Removed SIMD size dependence on -g. SIMD size is an optimization so it is dependent on whether optimizations are enabled.
• Removed the code related to replacing unreachable instructions with "return undef".
• Added an analysis to check if an instruction's def reaches the end of its parent basic block.
• Added Vector Compute backend
• Added build option, vISA_noStitchExternFunc, to control the stitching policy.
• Added extra condition for transforming ptr-arg.
• Fixed defect where 32word and 64word in align directives failed parse.
• Fixed DILocation for globals that are localized.
• Fixed payload coalesing missing issue for dual-source RTW on SIMD16.
• Move Accumulator substitution into its own file.
• Skipping marking source variables with Output attribute.
• CISA assembly update.
• SWSB improvements.
• Avoiding div by zero while doing spillCost computations.
• Write to null register when inlineAsm output is unused.
• Enhance stateless simple push to allow promoting regions where the starting address can be a sum of 2 runtime values.
• Increase the maximum size of arguments that can be passed to OpenCL kernel to 2 KB.
• Optimize double precision SQRT instruction.
• Do not include zero-sized variable (e.g., Arg/Retval when there's no stack call) in global RA.
• Do explicit var split for local live-ranges only.
• Support vector type for llvm.copysign
• Protecting ISA generated variables from conflicting with vISA keywords (vISA reserved words are suffixed with _ (iteratively)).
• Set push constant mode to gather if the driver only supports gather.
• DWARF debugger location expressions fixes.
• Turn off writing caller's frame-pointer to callee's stack. Since this feature is needed only for stack-walk, we can turn it off by default with compiler flag: EnableWriteOldFPToStack.

Ubuntu 18.04 binary packages for LLVM10/Clang10 are included.