[PATCH] D155681: [AMDGPU] Insert s_nop before s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
Jay Foad via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Jul 19 02:27:55 PDT 2023
foad updated this revision to Diff 541912.
foad added a comment.
Use a subtarget predicate function.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155681/new/
https://reviews.llvm.org/D155681
Files:
llvm/lib/Target/AMDGPU/GCNSubtarget.h
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_udec_wrap.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_uinc_wrap.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/extractelement.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/fmed3.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.i16.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.i8.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.large.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.div.fmas.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.div.scale.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.end.cf.i32.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.global.atomic.csub.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.if.break.i32.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.store.2d.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.is.private.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.is.shared.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.mov.dpp.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.update.dpp.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_32.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_64.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/load-unaligned.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/mul-known-bits.i64.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/shl-ext-reduce.ll
llvm/test/CodeGen/AMDGPU/add.v2i16.ll
llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll
llvm/test/CodeGen/AMDGPU/atomic_optimizations_raw_buffer.ll
llvm/test/CodeGen/AMDGPU/atomic_optimizations_struct_buffer.ll
llvm/test/CodeGen/AMDGPU/bitreverse.ll
llvm/test/CodeGen/AMDGPU/br_cc.f16.ll
llvm/test/CodeGen/AMDGPU/bswap.ll
llvm/test/CodeGen/AMDGPU/call-argument-types.ll
llvm/test/CodeGen/AMDGPU/calling-conventions.ll
llvm/test/CodeGen/AMDGPU/carryout-selection.ll
llvm/test/CodeGen/AMDGPU/chain-hi-to-lo.ll
llvm/test/CodeGen/AMDGPU/clamp-modifier.ll
llvm/test/CodeGen/AMDGPU/clamp.ll
llvm/test/CodeGen/AMDGPU/cluster_stores.ll
llvm/test/CodeGen/AMDGPU/ctlz.ll
llvm/test/CodeGen/AMDGPU/cvt_f32_ubyte.ll
llvm/test/CodeGen/AMDGPU/divergence-driven-buildvector.ll
llvm/test/CodeGen/AMDGPU/ds-sub-offset.ll
llvm/test/CodeGen/AMDGPU/expand-scalar-carry-out-select-user.ll
llvm/test/CodeGen/AMDGPU/extract_vector_elt-f16.ll
llvm/test/CodeGen/AMDGPU/fabs.f16.ll
llvm/test/CodeGen/AMDGPU/fadd.f16.ll
llvm/test/CodeGen/AMDGPU/fast-unaligned-load-store.global.ll
llvm/test/CodeGen/AMDGPU/fcanonicalize.f16.ll
llvm/test/CodeGen/AMDGPU/fcanonicalize.ll
llvm/test/CodeGen/AMDGPU/fcmp.f16.ll
llvm/test/CodeGen/AMDGPU/fcopysign.f16.ll
llvm/test/CodeGen/AMDGPU/fcopysign.f32.ll
llvm/test/CodeGen/AMDGPU/fcopysign.f64.ll
llvm/test/CodeGen/AMDGPU/fdiv.f16.ll
llvm/test/CodeGen/AMDGPU/fdiv.ll
llvm/test/CodeGen/AMDGPU/fma-combine.ll
llvm/test/CodeGen/AMDGPU/fmax3.ll
llvm/test/CodeGen/AMDGPU/fmed3.ll
llvm/test/CodeGen/AMDGPU/fmin3.ll
llvm/test/CodeGen/AMDGPU/fmul.f16.ll
llvm/test/CodeGen/AMDGPU/fnearbyint.ll
llvm/test/CodeGen/AMDGPU/fneg-fabs.f16.ll
llvm/test/CodeGen/AMDGPU/fneg-modifier-casting.ll
llvm/test/CodeGen/AMDGPU/fneg.f16.ll
llvm/test/CodeGen/AMDGPU/fp-classify.ll
llvm/test/CodeGen/AMDGPU/fp-min-max-buffer-atomics.ll
llvm/test/CodeGen/AMDGPU/fp-min-max-buffer-ptr-atomics.ll
llvm/test/CodeGen/AMDGPU/fp-min-max-global-atomics.ll
llvm/test/CodeGen/AMDGPU/fp16_to_fp32.ll
llvm/test/CodeGen/AMDGPU/fp16_to_fp64.ll
llvm/test/CodeGen/AMDGPU/fp32_to_fp16.ll
llvm/test/CodeGen/AMDGPU/fpext.f16.ll
llvm/test/CodeGen/AMDGPU/fptrunc.f16.ll
llvm/test/CodeGen/AMDGPU/fptrunc.ll
llvm/test/CodeGen/AMDGPU/frem.ll
llvm/test/CodeGen/AMDGPU/fshl.ll
llvm/test/CodeGen/AMDGPU/fshr.ll
llvm/test/CodeGen/AMDGPU/fsub.f16.ll
llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll
llvm/test/CodeGen/AMDGPU/global-saddr-atomics.ll
llvm/test/CodeGen/AMDGPU/global-saddr-store.ll
llvm/test/CodeGen/AMDGPU/half.ll
llvm/test/CodeGen/AMDGPU/idiv-licm.ll
llvm/test/CodeGen/AMDGPU/image-load-d16-tfe.ll
llvm/test/CodeGen/AMDGPU/imm16.ll
llvm/test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.pkrtz.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.add.gs.reg.rtn.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.bvh.stack.rtn.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.sub.gs.reg.rtn.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fcmp.w32.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fcmp.w64.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.bf16.bf16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.f16.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.f32.bf16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.icmp.w32.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.icmp.w64.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.a16.dim.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.a16.encode.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.dim.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.store.a16.d16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.store.a16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.inverse.ballot.i32.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.inverse.ballot.i64.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ldexp.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.permlane.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.permlane64.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.store.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.tbuffer.store.d16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.tbuffer.store.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.d16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.buffer.load.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.sendmsg.rtn.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.store.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.tbuffer.store.d16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.tbuffer.store.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.store.d16.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.store.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_32.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_64.ll
llvm/test/CodeGen/AMDGPU/llvm.ceil.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.floor.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.is.fpclass.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.is.fpclass.ll
llvm/test/CodeGen/AMDGPU/llvm.log.ll
llvm/test/CodeGen/AMDGPU/llvm.log10.ll
llvm/test/CodeGen/AMDGPU/llvm.log2.ll
llvm/test/CodeGen/AMDGPU/llvm.maxnum.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.minnum.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.mulo.ll
llvm/test/CodeGen/AMDGPU/llvm.rint.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.round.ll
llvm/test/CodeGen/AMDGPU/llvm.sin.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.sqrt.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.trunc.f16.ll
llvm/test/CodeGen/AMDGPU/lshr.v2i16.ll
llvm/test/CodeGen/AMDGPU/mad.u16.ll
llvm/test/CodeGen/AMDGPU/mad_64_32.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-global-agent.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-global-nontemporal.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-global-singlethread.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-global-system.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-global-volatile.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-global-wavefront.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-global-workgroup.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-local-nontemporal.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-local-volatile.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-private-nontemporal.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-private-volatile.ll
llvm/test/CodeGen/AMDGPU/minmax.ll
llvm/test/CodeGen/AMDGPU/mul.ll
llvm/test/CodeGen/AMDGPU/offset-split-global.ll
llvm/test/CodeGen/AMDGPU/omod.ll
llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.ll
llvm/test/CodeGen/AMDGPU/saddo.ll
llvm/test/CodeGen/AMDGPU/select.f16.ll
llvm/test/CodeGen/AMDGPU/shl.v2i16.ll
llvm/test/CodeGen/AMDGPU/shrink-add-sub-constant.ll
llvm/test/CodeGen/AMDGPU/sint_to_fp.i64.ll
llvm/test/CodeGen/AMDGPU/sitofp.f16.ll
llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
llvm/test/CodeGen/AMDGPU/sub.v2i16.ll
llvm/test/CodeGen/AMDGPU/uint_to_fp.i64.ll
llvm/test/CodeGen/AMDGPU/uitofp.f16.ll
llvm/test/CodeGen/AMDGPU/v_madak_f16.ll
llvm/test/CodeGen/AMDGPU/v_sat_pk_u8_i16.ll
llvm/test/CodeGen/AMDGPU/vector_shuffle.packed.ll
llvm/test/CodeGen/AMDGPU/widen-smrd-loads.ll
llvm/test/CodeGen/AMDGPU/wmma_multiple_32.ll
llvm/test/CodeGen/AMDGPU/wmma_multiple_64.ll
More information about the llvm-commits
mailing list