aboutsummaryrefslogtreecommitdiff
path: root/mlir/test/Conversion
AgeCommit message (Expand)AuthorFilesLines
2024-02-23[mlir][math] Propagate scalability in `convert-math-to-llvm` (#82635)Benjamin Maxwell1-0/+81
2024-02-22[TOSA] TosaToLinalg: fix int64_t min/max lowering of clamp (#82641)Matthias Gehre1-0/+15
2024-02-21[mlir] Use arith max or min ops instead of cmp + select (#82178)mlevesquedion6-162/+89
2024-02-20[mlir][VectorOps] Add unrolling for n-D vector.interleave ops (#80967)Benjamin Maxwell1-0/+24
2024-02-16[MLIR][OpenMP] Support `llvm` conversion for `omp.private` regions (#81414)Kareem Ergawy1-0/+26
2024-02-13[mlir][flang][openmp] Rework wsloop reduction operations (#80019)David Truby2-12/+32
2024-02-13[mlir][VectorOps] Add conversion of 1-D vector.interleave ops to LLVM (#80966)Benjamin Maxwell1-0/+37
2024-02-13[mlir][nvgpu] Make `phaseParity` of `mbarrier.try_wait` `i1` (#81460)Guray Ozen1-4/+4
2024-02-11[mlir][complex] Prevent underflow in complex.abs (#79786) (#81092)Kai Sasaki2-26/+126
2024-02-07[MLIR][VCIX] Support VCIX intrinsics in LLVMIR dialect (#75875)Kolya Panchenko1-0/+193
2024-02-07[TOSA] Fix avgpool2d accum in wider type (#80849)Thomas Preud'homme1-0/+91
2024-02-07[mlir][ArmSME] Support 4-way widening outer products (#79288)Cullen Rhodes1-0/+176
2024-02-05[mlir][EmitC] Add support for external functions (#80547)Marius Brehler1-0/+5
2024-02-05[mlir][nvgpu] Improve `tensormap.descriptor` Type Verifier (#77904)Guray Ozen1-10/+7
2024-02-01[mlir][spirv][memref] Calculate alignment for `PhysicalStorageBuffer`s (#80243)Jakub Kuderski1-4/+51
2024-02-01 [mlir][EmitC] Add func, call and return operations and conversions (#79612)Marius Brehler1-0/+55
2024-01-31Revert "[mlir][complex] Prevent underflow in complex.abs (#79786)"Benjamin Kramer2-126/+26
2024-01-31[mlir][ArmSME] Support 2-way widening outer products (#78975)Cullen Rhodes1-0/+96
2024-01-31[mlir][complex] Prevent underflow in complex.abs (#79786)Kai Sasaki2-26/+126
2024-01-30Fix TOSA FP16->INT16 CAST lowering (#79299)Thomas Preud'homme1-12/+27
2024-01-30[mlir] [arith] add shl overflow flag in Arith and lower to SPIR-V and LLVMIR ...Yi Wu2-0/+6
2024-01-29[mlir][gpu] Add support for lowering math.erf to __nv_erf (#79848)David Majnemer1-0/+13
2024-01-27Revert "[mlir][complex] Prevent underflow in complex.abs" (#79722)Mehdi Amini2-114/+26
2024-01-27[mlir][complex] Prevent underflow in complex.abs (#76316)Kai Sasaki2-26/+114
2024-01-26[mlir][ArmSME] Fix loop bounds of masked loads/stores (#78983)Benjamin Maxwell1-2/+16
2024-01-25[mlir][vector] Extend vector.{insert|extract}_strided_slice (#79052)Andrzej Warzyński1-0/+43
2024-01-25[mlir][ArmSME] Refactor ArmSMEToSCF to used shared loop-building helper (NFC)...Benjamin Maxwell1-2/+2
2024-01-25[mlir][nvgpu] Fix `transposeB` in `nvgpu.warpgroup.mma` (#79271)Guray Ozen1-9/+9
2024-01-23[mlir][ArithToAMDGPU] Add option for saturating truncation to fp8 (#74153)Krzysztof Drewniak2-19/+68
2024-01-22[mlir][ArmSME] Add arith-to-arm-sme conversion pass (#78197)Cullen Rhodes1-0/+129
2024-01-22[MLIR][NVVM] Update cp.async.bulk Ops to use intrinsics (#78900)Durgadoss R1-11/+7
2024-01-22[MLIR][NVVM] Explicit Data Type for Output in `wgmma.mma_async` (#78713)Guray Ozen3-58/+58
2024-01-22[mlir][nvgpu] Fix 'warpgroup.mma.store' index calculation (#78413)Guray Ozen1-0/+130
2024-01-18[mlir][complex] Convert complex.tan to libm ctan call (#78250)Kai Sasaki1-0/+14
2024-01-17[MLIR][LLVM] Add explicit target_cpu attribute to llvm.func (#78287)Sergio Afonso1-0/+10
2024-01-17[mlir][arith] Add overflow flags support to arith ops (#78376)Jacques Pienaar2-0/+53
2024-01-15[mlir][nvgpu] Add `nvgpu.tma.async.store` (#77811)Guray Ozen1-0/+46
2024-01-12[mlir][ArmSME] Add rudimentary support for tile spills to the stack (#76086)Benjamin Maxwell1-0/+154
2024-01-12[mlir][nvvm] Introduce `cp.async.bulk.wait_group` (#77917)Guray Ozen1-0/+17
2024-01-12Revert "[mlir][arith] Add overflow flags support to arith ops (#77211)"Ivan Butygin1-13/+0
2024-01-12Revert "[mlir][spirv] Lower `arith` overflow flags to corresponding SPIR-V op...Ivan Butygin1-40/+0
2024-01-11[mlir][spirv] Lower `arith` overflow flags to corresponding SPIR-V op decorat...Ivan Butygin1-0/+40
2024-01-11[TOSA] FFT2D operator (#77005)Dmitriy Smirnov1-0/+134
2024-01-10[MLIR][NVVM]: Update setmaxregister NVVM Op (#77594)Durgadoss R1-2/+3
2024-01-10[mlir][tosa]Fix Rescale shift attr data type (#71084)Tai Ly1-14/+14
2024-01-10[mlir][math] Add math.acosh|asin|asinh|atanh op (#77463)Vivek Khandelwal1-0/+166
2024-01-10[mlir][ArmSME] Add arm_sme.streaming_vl operation (#77321)Benjamin Maxwell1-0/+42
2024-01-10[mlir][arith] Add overflow flags support to arith ops (#77211)Ivan Butygin1-0/+13
2024-01-09[mlir][Vector] Add nontemporal attribute, mirroring memref (#76752)Krzysztof Drewniak1-0/+29
2024-01-09[mlir][gpu] Use DenseI32Array for NVVM's maxntid and reqntid (NFC) (#77466)Guray Ozen1-1/+1
generated by cgit v1.1 at 2024-09-07 08:49:09 +0000