summaryrefslogtreecommitdiff
path: root/mlir/lib/Conversion/ArithToAMDGPU
AgeCommit message (Expand)Author
2025-10-30[mlir] Simplify Default cases in type switches. NFC. (#165767)Jakub Kuderski
2025-10-10[MLIR][Vector] Remove vector.splat (#162167)James Newling
2025-09-19[mlir][arith] Simplify inheriting constructors declarations. NFC. (#159682)Jakub Kuderski
2025-09-17[mlir][ArithToAMDGPU] limit scaling truncf/extf support to gfx950 (#155431)Muzammil
2025-07-24[mlir][ArithToAMDGPU] Use native packing support (#150342)Krzysztof Drewniak
2025-07-23[mlir][NFC] update `Conversion` create APIs (4/n) (#149879)Maksim Levental
2025-07-23[mlir][ArithToAMDGPU][NFC] Add PatternBenefit (#150091)Krzysztof Drewniak
2025-07-21[mlir][vector] Support direct broadcast conversion (LLVM & SPIRV) (#148027)James Newling
2025-07-08[mlir][amdgpu] Add conversion from arith.scaling_extf / arith.scaling_truncf ...Tim Gymnich
2025-03-21[AMD][ROCDL] Add packed conversions fp8/bf8->bf16 and fp8/bf8->fp32 in ROCDL ...Yi Qian
2025-03-07[mlir][IR] Deprecate `match` and `rewrite` functions (#130031)Matthias Springer
2025-03-06[mlir][IR] Move `match` and `rewrite` functions into separate class (#129861)Matthias Springer
2025-03-03[MLIR][AMDGPU] Add OCP FP8 support for new hardware (#127728)Mirza Halilčević
2025-02-19[AMDGPU][MLIR] Replace gfx940 and gfx941 with gfx942 in MLIR (#125836)Fabian Ritter
2025-02-07[mlir][amdgpu] Support for 8bit extf for 0d vector type (#126102)Prashant Kumar
2025-01-20[mlir][IR] Remove `isF...()` type API for low-precision FP types (#123326)Matthias Springer
2024-12-20[mlir] Enable decoupling two kinds of greedy behavior. (#104649)Jacques Pienaar
2024-11-13[mlir][Vector] Remove trivial uses of vector.extractelement/vector.insertelem...Kunwar Grover
2024-09-09[mlir][amdgpu] Align Chipset with TargetParser (#107720)Jakub Kuderski
2024-08-26[MLIR][AMDGPU] Introduce fp16 packed arithmetic (#105688)Giuseppe Rossini
2024-07-09[mlir][amdgpu] Add support for multi-dim arith.truncf/extf fp8 lowering (#98074)Rob Suderman
2024-07-02mlir/LogicalResult: move into llvm (#97309)Ramkumar Ramachandra
2024-04-19Switch member calls to `isa/dyn_cast/cast/...` to free function calls. (#89356)Christian Sigg
2024-04-01[MLIR][Arith] Add rounding mode attribute to `truncf` (#86152)Victor Perez
2024-01-31[mlir] Use `create` instead of `createOrFold` for ConstantOp as folding has n...Hugo Trachino
2024-01-23[mlir][ArithToAMDGPU] Add option for saturating truncation to fp8 (#74153)Krzysztof Drewniak
2023-09-28[mlir][AMDGPU] Add packed 8-bit float conversion ops and loweringKrzysztof Drewniak
generated by cgit v1.2.3 (git 2.25.1) at 2026-07-27 08:58:58 +0000