Use the 64-bit SGPR base with a 0 offset, since it's 1 fewer
instructions to materialize the 0 vs. the 64-bit copy.
Details
Details
Diff Detail
Diff Detail
Paths
| Differential D91390
AMDGPU: Select global saddr mode from SGPR pointer ClosedPublic Authored by arsenm on Nov 12 2020, 1:40 PM.
Details
Diff Detail Event Timelinearsenm added a parent revision: D91308: AMDGPU: Split large offsets when selecting global saddr mode.Nov 12 2020, 1:40 PM This revision is now accepted and ready to land.Nov 12 2020, 1:44 PM
Revision Contents
Diff 304963 llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
llvm/test/CodeGen/AMDGPU/GlobalISel/extractelement.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement-stack-lower.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.i16.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.i8.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-amdgpu-atomic-cmpxchg-global.mir
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-copy.mir
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fract.f64.mir
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-load-global-saddr.mir
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.atomic.inc.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.image.load.2d.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.load.2darraymsaa.a16.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.load.2darraymsaa.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.load.3d.a16.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.load.3d.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/load-constant.96.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/localizer.ll
llvm/test/CodeGen/AMDGPU/GlobalISel/non-entry-alloca.ll
llvm/test/CodeGen/AMDGPU/addrspacecast.ll
llvm/test/CodeGen/AMDGPU/amdpal-elf.ll
llvm/test/CodeGen/AMDGPU/call-waitcnt.ll
llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-gfx1030.ll
llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-gfx908.ll
llvm/test/CodeGen/AMDGPU/cgp-addressing-modes.ll
llvm/test/CodeGen/AMDGPU/chain-hi-to-lo.ll
llvm/test/CodeGen/AMDGPU/dagcombine-select.ll
llvm/test/CodeGen/AMDGPU/ds_read2.ll
llvm/test/CodeGen/AMDGPU/fabs.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/fdiv32-to-rcp-folding.ll
llvm/test/CodeGen/AMDGPU/fneg-fabs.f16.ll
llvm/test/CodeGen/AMDGPU/fneg.f16.ll
llvm/test/CodeGen/AMDGPU/fshl.ll
llvm/test/CodeGen/AMDGPU/fshr.ll
llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll
llvm/test/CodeGen/AMDGPU/global-atomics-fp.ll
llvm/test/CodeGen/AMDGPU/global-saddr-load.ll
llvm/test/CodeGen/AMDGPU/global_atomics.ll
llvm/test/CodeGen/AMDGPU/global_atomics_i64.ll
llvm/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props-v3.ll
llvm/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props.ll
llvm/test/CodeGen/AMDGPU/hsa.ll
llvm/test/CodeGen/AMDGPU/idiv-licm.ll
llvm/test/CodeGen/AMDGPU/idot2.ll
llvm/test/CodeGen/AMDGPU/idot4s.ll
llvm/test/CodeGen/AMDGPU/idot4u.ll
llvm/test/CodeGen/AMDGPU/idot8s.ll
llvm/test/CodeGen/AMDGPU/idot8u.ll
llvm/test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
llvm/test/CodeGen/AMDGPU/kernel-args.ll
llvm/test/CodeGen/AMDGPU/kernel-argument-dag-lowering.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.atomic.csub.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.atomic.dec.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.atomic.fadd.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.atomic.inc.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.pkrtz.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.dim.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.d16.dim.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.dim.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.get.waveid.in.workgroup.ll
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wavefrontsize.ll
llvm/test/CodeGen/AMDGPU/llvm.cos.f16.ll
llvm/test/CodeGen/AMDGPU/llvm.sin.f16.ll
llvm/test/CodeGen/AMDGPU/load-global-i32.ll
llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
llvm/test/CodeGen/AMDGPU/lshr.v2i16.ll
llvm/test/CodeGen/AMDGPU/mad.u16.ll
llvm/test/CodeGen/AMDGPU/mai-inline.ll
llvm/test/CodeGen/AMDGPU/memory-legalizer-store.ll
llvm/test/CodeGen/AMDGPU/memory_clause.ll
llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll
llvm/test/CodeGen/AMDGPU/offset-split-global.ll
llvm/test/CodeGen/AMDGPU/promote-alloca-vector-to-vector.ll
llvm/test/CodeGen/AMDGPU/readcyclecounter.ll
llvm/test/CodeGen/AMDGPU/saddo.ll
llvm/test/CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll
llvm/test/CodeGen/AMDGPU/smrd_vmem_war.ll
llvm/test/CodeGen/AMDGPU/store-global.ll
llvm/test/CodeGen/AMDGPU/store-weird-sizes.ll
llvm/test/CodeGen/AMDGPU/trunc-store-i64.ll
llvm/test/CodeGen/AMDGPU/vector_shuffle.packed.ll
llvm/test/CodeGen/AMDGPU/wave32.ll
|