mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-14 11:32:34 +00:00
e08f05f3a5
Summary:
According to PTX ISA:
For convenience, ld, st, and cvt instructions permit source and destination data operands to be wider than the instruction-type size, so that narrow values may be loaded, stored, and converted using regular-width registers. For example, 8-bit or 16-bit values may be held directly in 32-bit or 64-bit registers when being loaded, stored, or converted to other types and sizes. The operand type checking rules are relaxed for bit-size and integer (signed and unsigned) instruction types; floating-point instruction types still require that the operand type-size matches exactly, unless the operand is of bit-size type.
So, the ISA does not support load with extending/store with truncatation for floating numbers. This is reflected in setting the loadext/truncstore actions to expand in the code for floating numbers, but vectors of floating numbers are not taken care of.
As a result, loading a vector of floats followed by a fp_extend may be combined by DAGCombiner to a extload, and the extload may be lowered to NVPTXISD::LoadV2 with extending information. However, NVPTXISD::LoadV2 does not perform extending, and no extending instructions are inserted. Finally, PTX instructions with mismatched types are generated, like
ld.v2.f32 {%fd3, %fd4}, [%rd2]
This patch adds the correct actions for vectors of floats, so DAGCombiner would not create loads with extending, and correct code is generated.
Patched by Gang Hu.
Test Plan: Test case attached.
Reviewers: jingyue
Reviewed By: jingyue
Subscribers: llvm-commits, jholewinski
Differential Revision: http://reviews.llvm.org/D10876
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241191 91177308-0d34-0410-b5e6-96231b3b80d8
|
||
|---|---|---|
| .. | ||
| access-non-generic.ll | ||
| add-128bit.ll | ||
| addrspacecast-gvar.ll | ||
| addrspacecast.ll | ||
| aggr-param.ll | ||
| annotations.ll | ||
| arg-lowering.ll | ||
| arithmetic-fp-sm20.ll | ||
| arithmetic-int.ll | ||
| atomics.ll | ||
| bfe.ll | ||
| bug17709.ll | ||
| bug21465.ll | ||
| bug22246.ll | ||
| bug22322.ll | ||
| call-with-alloca-buffer.ll | ||
| callchain.ll | ||
| calling-conv.ll | ||
| compare-int.ll | ||
| constant-vectors.ll | ||
| convert-fp.ll | ||
| convert-int-sm20.ll | ||
| ctlz.ll | ||
| ctpop.ll | ||
| cttz.ll | ||
| div-ri.ll | ||
| envreg.ll | ||
| extloadv.ll | ||
| fast-math.ll | ||
| fma-assoc.ll | ||
| fma-disable.ll | ||
| fma.ll | ||
| fp16.ll | ||
| fp-contract.ll | ||
| fp-literals.ll | ||
| function-align.ll | ||
| generic-to-nvvm.ll | ||
| global-ordering.ll | ||
| globals_init.ll | ||
| globals_lowering.ll | ||
| gvar-init.ll | ||
| half.ll | ||
| i1-global.ll | ||
| i1-int-to-fp.ll | ||
| i1-param.ll | ||
| i8-param.ll | ||
| imad.ll | ||
| implicit-def.ll | ||
| inline-asm.ll | ||
| intrin-nocapture.ll | ||
| intrinsic-old.ll | ||
| intrinsics.ll | ||
| isspacep.ll | ||
| ld-addrspace.ll | ||
| ld-generic.ll | ||
| ldparam-v4.ll | ||
| ldu-i8.ll | ||
| ldu-ldg.ll | ||
| ldu-reg-plus-offset.ll | ||
| lit.local.cfg | ||
| load-sext-i1.ll | ||
| local-stack-frame.ll | ||
| lower-alloca.ll | ||
| lower-kernel-ptr-arg.ll | ||
| machine-sink.ll | ||
| managed.ll | ||
| misaligned-vector-ldst.ll | ||
| module-inline-asm.ll | ||
| mulwide.ll | ||
| noduplicate-syncthreads.ll | ||
| nounroll.ll | ||
| nvcl-param-align.ll | ||
| nvvm-reflect.ll | ||
| param-align.ll | ||
| pr13291-i1-store.ll | ||
| pr16278.ll | ||
| pr17529.ll | ||
| refl1.ll | ||
| rotate.ll | ||
| rsqrt.ll | ||
| sched1.ll | ||
| sched2.ll | ||
| sext-in-reg.ll | ||
| sext-params.ll | ||
| shift-parts.ll | ||
| simple-call.ll | ||
| sm-version-20.ll | ||
| sm-version-21.ll | ||
| sm-version-30.ll | ||
| sm-version-32.ll | ||
| sm-version-35.ll | ||
| sm-version-37.ll | ||
| sm-version-50.ll | ||
| sm-version-52.ll | ||
| sm-version-53.ll | ||
| st-addrspace.ll | ||
| st-generic.ll | ||
| surf-read-cuda.ll | ||
| surf-read.ll | ||
| surf-write-cuda.ll | ||
| surf-write.ll | ||
| symbol-naming.ll | ||
| tex-read-cuda.ll | ||
| tex-read.ll | ||
| texsurf-queries.ll | ||
| tuple-literal.ll | ||
| vec8.ll | ||
| vec-param-load.ll | ||
| vector-args.ll | ||
| vector-call.ll | ||
| vector-compare.ll | ||
| vector-global.ll | ||
| vector-loads.ll | ||
| vector-return.ll | ||
| vector-select.ll | ||
| vector-stores.ll | ||
| weak-global.ll | ||
| weak-linkage.ll | ||