This is an automated email from the ASF dual-hosted git repository.
spectrometerHBH pushed a change to branch tir-bench
in repository https://gitbox.apache.org/repos/asf/tvm.git
was cd8790bc54 feat(infra): util-gated GPU selection for tir-bench +
per-config warmup/repeat
This change permanently discards the following revisions:
discard cd8790bc54 feat(infra): util-gated GPU selection for tir-bench +
per-config warmup/repeat
discard aa035ff69f fix(arith): memoize IntervalSet variable relaxation to
avoid exponential blowup (#652)
discard f715671412 fix(arith): gate canonical-simplify LT Case 2 on extra
scale == +1 (#651)
discard 010246e61f feat(infra): add tir-bench slash command for pre-commit
regression check (#650)
discard aef7bd7e97 feat(gemm_async): accept Layout F C operand for M=64 MMAs
(#648)
discard 714a795729 revert(submodules): undo accidental 3rdparty pointer bumps
in #646 (#647)
discard ce87b82cc4 feat(tirx): add M=128 dispatch + layout for .16x*b
tcgen05.ld/st (#646)
discard 3432c72a50 refactor(op-dispatch): ewise broadcast at layout level +
copy vec-alignment fix (#645)
discard e3271628f4 feat(tirx): add .16x{64,128,256}b tcgen05.ld/st dispatch +
factory (#644)
discard aff1a6ce34 refactor(op-dispatch): split CUDA copy into reg + gmem_smem
+ ldgsts (#640)
discard a394fd58b0 docs: update tir bench baseline results (#642)
discard bad4d0a932 feat(tirx): add typed pointer byte-offset intrinsic (#641)
discard b148ee5f5f refactor(lower-tirx): drop Tx.filter wrapper for canonical
thread filters (#638)
discard bb57b65fd8 fix(tirx/stmt_functor): add ScopeIdDefStmt to Python
StmtFunctor dispatch (#637)
discard bb15ecc80a refactor(lower-tirx): replace ScopeKind::kKernel with
Tx.device_entry() marker (#636)
discard 36b274d738 feat(tvmscript): add @Tx.jit decorator, Tx.constexpr
params, Tx.wg_reg_tile (#635)
discard d4b9e91923 refactor(codegen): remove tirx.entry_cluster_sync codegen
attribute (#634)
discard 7ea22041de test(op-dispatch): add wg-scope both-sides-permuted
invariance test (#632) (#633)
discard 7addfb1da2 refactor(op-dispatch): rename copy/warp_matrix.py to
copy/ld_stmatrix.py (#631)
discard 6053f82fcc feat(op-dispatch): add warp ldmatrix/stmatrix dispatch for
Tx.copy (#630)
discard f7f287f88f feat(op): add permute_layout primitive; remove permute_dims
(#629)
discard 52ecb035ec tirx
