microsoft/Accera

📋 What's Changed

• ------------
• Merged PR 3211: Upgrade hatlib dependency to 0.0.39. [Captain Jack
• Sparrow]
• Upgrade hatlib dependency to 0.0.39
• Merged PR 3209: Support AffineParallelOp and scf::ParallelOp in
• RangeValue utils. [Mason Remy]
• Support AffineParallelOp and scf::ParallelOp in RangeValue utils
• Merged PR 3207: Fix parallelization and enable file checker in tests.
• + 29 more

📋 What's Changed

• Merged PR 3199: Rename _slice to slice and add docs. [Captain Jack
• Sparrow]
• Rename _slice to slice and add docs
• Merged PR 3197: Preserve dest memref shape during SliceOp to SubViewOp
• lowering. [Captain Jack Sparrow]
• Preserve dest memref shape during SliceOp to SubViewOp lowering:
• Without this change, subview op would discard the dest memref type required by the slice op. For example,
• ```
• + 52 more

📋 Changes

• Merged PR 3181: Fix bug with reinterpret_cast of partially-dynamic
• Merged PR 3180: Enable getting a memref shape from a memref_cast
• Merged PR 3179: Fix vulkan-specific smoke test break. [Lisa Ong]

📋 Changes

• Merged PR 3176: [Accera] split_dim op supports dynamic dims with
• Merged PR 3174: Ensure any dynamic allocations are heap allocs that
• Merged PR 3171: [test] Add some tests for Dimensions. [Kern Handa]
• Merged PR 3175: Support reinterpret cast of same bitwidth without
• Merged PR 3167: Remove hack to treat INPUT_OUTPUT Arrays with shape
• Merged PR 3165: [build] Fix clang 14 release build warnings treated as
• Merged PR 3162: Bump vcpkg to latest release. [Lisa Ong]
• Merged PR 3161: Fix cache reduce scale constant hoisting. [Mason Remy]
• + 1 more

📋 Changes

• Merged PR 3160: [security] bump onnx to 1.13.0. [Lisa Ong]
• Merged PR 3157: Dynamic split dim tests. [Mason Remy]
• Merged PR 3158: Do not unroll the profiling ops when vectorization
• Merged PR 3153: Fix the lowering issue of the profiling ops. [Denny
• Merged PR 3152: [nfc] [test] Skip fast_exp mlas tests on unsupported

📋 Changes

• Merged PR 3150: Change high precision fp to not perform contraction.
• Merged PR 3147: Fix vector cast with same bitwidth. [Mason Remy]
• Merged PR 3149: Improve 1-D horizontal sum reductions for 8xf32 and
• Merged PR 3148: Adds Package level FP precision override. [Kern Handa]
• Merged PR 3144: Removes fp precision as an option for Package.build.
• Merged PR 3143: Add dsl test for profiling op. [Denny Sun]
• Merged PR 3022: Assert the arg order in debug mode. [Denny Sun]
• Merged PR 3137: expose profiling function to DSL. [Denny Sun]
• + 10 more

📋 Changes

• Merged PR 3131: Set masked load/store inbounds flag to true. [Mason
• Merged PR 3130: Recognize and simplify always true EQ and NE CmpOps.
• Merged PR 3129: Optimize 1-row horizontal i16->i32 sum reduction.
• Merged PR 3118: vectorize accumulation of results of two masked load
• Merged PR 3126: [test] Adds more tests for vectorized transpose. [Kern
• Merged PR 3121: [nfc] Separate bounds checking into separate pass
• Merged PR 3122: Fix reinterpret_cast output memref shape. [Mason Remy]
• Merged PR 3115: Normalize AffineForOps to have unit stride and begin
• + 2 more

📋 Changes

• Merged PR 3107: Make vectorization happen after inlining and
• Merged PR 3108: extend vectorization for masked store case. [JUBI
• Merged PR 3109: Set conan version < 2.0.0. [Mason Remy]
• Merged PR 3104: Position fusing dim after the fused dimensions.
• Merged PR 3096: Add "RelWithDebInfo"-like option to accc. [Chuck

📋 Changes

• Merged PR 3101: [build] install pkg-config for macos buddy builds.
• Merged PR 3098: [nfc] Move vectorization code to separate files.
• Merged PR 3100: Adds CMake dependencies to acc-translate to ensure
• Merged PR 3095: Remove duplicate SubArray class. [Mason Remy]
• Merged PR 3073: vectorize masked load store. [JUBI TANEJA]
• Merged PR 3093: Add meaningful error messages for c++ exceptions.
• Merged PR 3092: Add type size getter utility. [Captain Jack Sparrow]
• Merged PR 3074: Add rudimentary pass to fix redundant load/store
• + 13 more

📋 What's Changed

• Merged PR 3070: Fixes for sub_array and _split_dimension [Mason Remy]
• Fixes for sub_array and _split_dimension
• This fixes the sub array and split dim ops to work with the accera
• codebase that has updated around them. Some MemoryLayout assumptions are
• getting in the way and have been disabled in the short-term, however
• long term our memory layout behavior should more closely match what MLIR
• affine maps can represent for more generalized dynamic support
• Merged PR 3063: Refactor Dimension with C++ backend container class and few other fixes [Captain Jack Sparrow]
• + 6 more

📋 Changes

• Merged PR 3069: Set target device features on module and check when
• Merged PR 3060: Adds support for sqrt op in acc-translate. [Kern

📋 Changes

• Merged PR 3055: Move value unrolling to after function inlining and
• Merged PR 3053: Add package.build flags for building with higher-
• Merged PR 3052: Place heap allocations at the top level of the
• Merged PR 3050: [non-func, API] Change Nest.get_shape() to always
• Merged PR 3030: Include acc-translate whenever accera is installed.
• Merged PR 3035: [nfc] Adds my machine to targets.py. [Kern Handa]

📋 What's Changed

• Merged PR 3029: Work around constraint resolution issues with dynamic
• split size 1. [Mason Remy]
• Work around constraint resolution issues with dynamic split size 1
• Full Changelog: https://github.com/microsoft/Accera/compare/v1.2.16...v1.2.17

📋 What's Changed

• Merged PR 3027: Hack required to use Array as output element argument
• (Dimension) [Captain Jack Sparrow]
• Merged PR 3025: Add arg name and size string required for hat
• metadata. [Captain Jack Sparrow]
• Add arg name and size string required for hat metadata
• Merged PR 3017: Output array supports gather function. [Denny Sun]
• Add the dsl test for gather function.
• Full Changelog: https://github.com/microsoft/Accera/compare/v1.2.15...v1.2.16

📋 What's Changed

• Merged PR 3018: Use VS 17.4.3-built binaries. This is in a separate
• channel to allow older ve... [Mason Remy]
• Use VS 17.4.3-built binaries. This is in a separate channel to allow older versions to keep working
• Merged PR 3012: Correctness check for output array support for range
• node. [Denny Sun]
• Successful correctness check means output array support can work end to end.
• Merged PR 3015: Update hatlib version to support floating type as
• function arg. [Denny Sun]
• + 13 more

📋 Changes

• Merged PR 3001: [test] Expect failures on macos for x86 intrinsics
• Merged PR 3000: Expect failures for macos in vpmaddwd tests. [Lisa
• Merged PR 2994: Bump hatlib to 0.0.32. [Lisa Ong]
• Merged PR 2997: Support more casting cases in vpmaddwd matcher. [Mason
• Merged PR 2996: [release] bump docs to 1.2.14 for next release. [Lisa

📋 Changes

• Merged PR 2987: Add support for max/min/round ops and vectorizing
• Merged PR 2963: Control TEMP array allocation location. [Mason Remy]
• Merged PR 2962: Expand vpmaddwd matching and add intrinsic call.
• Merged PR 2961: Match more vectorization patterns and support
• 2-loop interleaving store -> vector shuffle and store
• simple horizontal reductions (not always efficient currently)
• vectorized casts
• Merged PR 2960: Enable marking functions as no-inline-into. [Mason
• + 10 more

📋 What's Changed

• Merged PR 2953: Workaround debug mode failures with dimension argument
• ordering. [Lisa Ong]
• Order dimension arguments after Array args to avoid this lowering issue in Debug mode (until Debug mode is fixed)
• ```
• %42 = llvm.insertvalue %7, %41[3, 0] : !llvm.struct<(ptr<f32>, ptr<f32>, i64, array<2 x i64>, array<2 x i64>)>
• ^
• %7 = llvm.insertvalue %arg6, %6[4, 1] : !llvm.struct<(ptr<f32>, ptr<f32>, i64, array<2 x i64>, array<2 x i64>)>
• ^
• + 61 more

📋 What's Changed

• Update vcpkg by @AtariDreams in https://github.com/microsoft/Accera/pull/52
• Merged PR 2924: Update hatlib dependency in setup.cfg, add comment.
• [Lisa Ong]
• Merged PR 2922: [Github] Update vcpkg. [Lisa Ong]
• From c2177e64bdf05e7ea69a8d41f420fcdb42df49db Mon Sep 17 00:00:00 2001
• Merged PR 2910: Updates hatlib dependency to 0.0.29. [Kern Handa]
• Merged PR 2905: Fix internal param name in GPU benchmarks. [Captain
• Jack Sparrow]
• + 47 more

✨ New Contributors

• @AtariDreams made their first contribution in https://github.com/microsoft/Accera/pull/52
• Full Changelog: https://github.com/microsoft/Accera/compare/v1.2.10...v1.2.11

📋 What's Changed

• Update ci.yml to fix path changes by @lisaong in https://github.com/microsoft/Accera/pull/49
• Add unrolled convolution case study link by @marina-neseem in https://github.com/microsoft/Accera/pull/50
• Bump protobuf from 3.20.1 to 3.20.2 in /accera/onnx-emitter/test by @dependabot in https://github.com/microsoft/Accera/pull/51
• Merged PR 2886: [release] Bump docs to 1.2.10, sync GH to ADO. [Lisa
• Ong]
• Bulk docs version update
• Bump protobuf from 3.20.1 to 3.20.2 in /accera/onnx-emitter/test (d1b87ec6820417da0e86d60094eacf354398d4b9)
• Also fixing a minor docs bug (errant backtick)
• + 74 more

📋 Changes

• Merged PR 2862: write runtime size of index type to Hat. [Denny Sun]
• Merged PR 2861: Fix cache_C benchmark variable which is not getting
• Merged PR 2864: [build]: fix breaks due to agent image updates. [Lisa
• Only pipelines that rely on azure build agents are affected.
• We still need to keep the submodule around to enable external builds from the Github repo.
• Remove defunct pipeline
• Update vcpkg submodule while we're here
• Merged PR 2839: Enable CUDA output caching. [Ritwik Das]
• + 37 more

📋 What's Changed

• Set license field in metadata of package by @tonybaloney in https://github.com/microsoft/Accera/pull/46
• Github codespaces configuration by @lisaong in https://github.com/microsoft/Accera/pull/48
• ------------
• Merged PR 2814: Parameterize batch_size in GPU benchmarks. [Ritwik
• Das]
• Parameterize batch_size in GPU benchmarks
• Merged PR 2810: [release] [nfc] Bump docs version to 1.2.8, bump
• github actions to llvm 14.0.6. [Lisa Ong]
• + 189 more

✨ New Contributors

• @tonybaloney made their first contribution in https://github.com/microsoft/Accera/pull/46
• Full Changelog: https://github.com/microsoft/Accera/compare/v1.2.7...v1.2.8

📋 Changes

• Merged PR 2744: [doc] Fixes link in reference/functions/cast.md, revs
• Merged PR 2743: [DSL] Document implicit casting rules and the explicit
• Document implicit casting rules implemented by !2693
• Promote `acc.cast` to a documented function to give the user control to override implicit casting behavior
• Merged PR 2739: Updates ROCM tensorization pattern to handle casting.
• Merged PR 2643: Some fixes for last major array caching in
• Merged PR 2693: Updates DSL codegen to implicitly cast if possible.
• Merged PR 2735: Pass multiple input files as comma-separated list to
• + 11 more

📋 What's Changed

• Bump urllib3 from 1.25.8 to 1.26.5 in /tools/benchmarkers by @dependabot in https://github.com/microsoft/Accera/pull/42
• [ci] Fix out of disk space errors for CI workflow by @lisaong in https://github.com/microsoft/Accera/pull/43
• Bump bottle from 0.12.19 to 0.12.20 in /tools/viz by @dependabot in https://github.com/microsoft/Accera/pull/44
• Merged PR 2657: Add conversion pass from gpu ops to rocdl ops. [Ritwik Das]
• switch to gpu dialect for gpu index ops
• add conversion pass from gpu dialect to rocdl
• Merged PR 2652: Add integer tensor ops support for AMD targets.
• [Ritwik Das]
• + 303 more

✨ New Contributors

• @dependabot made their first contribution in https://github.com/microsoft/Accera/pull/42
• Full Changelog: https://github.com/microsoft/Accera/compare/v1.2.5...v1.2.6

📋 What's Changed

• Add link to the NCHWc 2D Convolution Case Study by @marina-neseem in https://github.com/microsoft/Accera/pull/41
• Merged PR 2593: [docs] [release] bump docs version to 1.2.5 in
• preparation for release. [Lisa Ong]
• bump docs version to 1.2.5 in preparation for release
• Merged PR 2586: Loop order and indices as parameters​ [Denny Sun]
• With this change, the user can write a schedule with loop_order parameterized:
• loop_order = create_parameters()
• schedule.reorder(order=loop_order )
• + 119 more

✨ New Contributors

• @marina-neseem made their first contribution in https://github.com/microsoft/Accera/pull/41
• Full Changelog: https://github.com/microsoft/Accera/compare/v1.2.4...v1.2.5

📋 What's Changed

• Docs refactoring install by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/27
• Revise Pi3_Cross_Compilation.md by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/28
• Docs refactoring tutorials hello matmul by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/29
• Docs refactoring tutorials hello matmul gpu by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/30
• Docs refactoring tutorials optimized matmul by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/31
• Refactoring of Accera.md from reference docs by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/32
• Complete refactoring of safety analysis by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/33
• Refactoring of functions docs in reference files by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/34
• + 208 more

📋 What's Changed

• Docs refactoring manual fusing by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/26
• Merged PR 2508: [release] Bump docs version to 1.2.3. [Lisa Ong]
• In preparation for a PyPI release to facilitate community contributions for case studies
• Synced doc editorials from public Github repo
• Merged PR 2503: [prog] Support unsigned integer types in the DSL.
• [Lisa Ong]
• Add ScalarType.uint8/16/32/64 support
• Use UnrealizedConversionCastOps to convert these unsigned ints to signless ints
• + 145 more

📋 What's Changed

• Full Changelog: https://github.com/microsoft/Accera/compare/v1.2.1...v1.2.2
• Add Ubuntu CI workflow by @lisaong in https://github.com/microsoft/Accera/pull/9
• Rework documentation sections by @lisaong in https://github.com/microsoft/Accera/pull/8
• Manually run script to update doc versions by @lisaong in https://github.com/microsoft/Accera/pull/10
• Show more perf gains for the quickstart example by @lisaong in https://github.com/microsoft/Accera/pull/12
• Fix post merge build break by @lisaong in https://github.com/microsoft/Accera/pull/14
• README.md refactoring by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/13
• Complete refactoring of file array.md and simple affine loop nests.md file in manual docs by @Arslan-e-Mustafa in https://github.com/microsoft/Accera/pull/16
• + 420 more

✨ New Contributors

• @Arslan-e-Mustafa made their first contribution in https://github.com/microsoft/Accera/pull/13

📋 What's Changed

• Merged PR 2391: Update quickstart example, updated docs structure per
• feedback. [Lisa Ong]
• Teasers for transformations in the Quickstart sample (to differentiate Accera from others), with benchmarking
• Removed the Miscellaneous section, redistributed various docs to various related locations
• Renamed the cross compilation tutorial so that it is ordered last
• Merged PR 2392: Populate Target.Models based on known devices. [Kern
• Handa]
• Populate Target.Models based on known devices
• + 502 more