mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 21:13:02 +02:00
e3fb38059f
Summary: Previously if you had * a function with the fast-math-enabled attr, followed by * a function without the fast-math attr, the second function would inherit the first function's fast-math-ness. This means that mixing fast-math and non-fast-math functions in a module was completely broken unless you explicitly annotated every non-fast-math function with "unsafe-fp-math"="false". This appears to have been broken since r176986 (March 2013), when the resetTargetOptions function was introduced. This patch tests the correct behavior as best we can. I don't think I can test FPDenormalMode and NoTrappingFPMath, because they aren't used in any backends during function lowering. Surprisingly, I also can't find any uses at all of LessPreciseFPMAD affecting generated code. The NVPTX/fast-math.ll test changes are an expected result of fixing this bug. When FMA is disabled, we emit add as "add.rn.f32", which prevents fma combining. Before this patch, fast-math was enabled in all functions following the one which explicitly enabled it on itself, so we were emitting plain "add.f32" where we should have generated "add.rn.f32". Reviewers: mkuper Subscribers: hfinkel, majnemer, jholewinski, nemanjai, llvm-commits Differential Revision: https://reviews.llvm.org/D28507 llvm-svn: 291618 |
||
|---|---|---|
| .. | ||
| access-non-generic.ll | ||
| add-128bit.ll | ||
| addrspacecast-gvar.ll | ||
| addrspacecast.ll | ||
| aggr-param.ll | ||
| aggregate-return.ll | ||
| alias.ll | ||
| annotations.ll | ||
| arg-lowering.ll | ||
| arithmetic-fp-sm20.ll | ||
| arithmetic-int.ll | ||
| atomics-with-scope.ll | ||
| atomics.ll | ||
| bfe.ll | ||
| branch-fold.ll | ||
| bug17709.ll | ||
| bug21465.ll | ||
| bug22246.ll | ||
| bug22322.ll | ||
| bug26185-2.ll | ||
| bug26185.ll | ||
| bypass-div.ll | ||
| call-with-alloca-buffer.ll | ||
| callchain.ll | ||
| calling-conv.ll | ||
| combine-min-max.ll | ||
| compare-int.ll | ||
| constant-vectors.ll | ||
| convergent-mir-call.ll | ||
| convert-fp.ll | ||
| convert-int-sm20.ll | ||
| ctlz.ll | ||
| ctpop.ll | ||
| cttz.ll | ||
| debug-file-loc.ll | ||
| disable-opt.ll | ||
| div-ri.ll | ||
| divrem-combine.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-ir.ll | ||
| generic-to-nvvm.ll | ||
| global-addrspace.ll | ||
| global-ctor-empty.ll | ||
| global-ctor.ll | ||
| global-dtor.ll | ||
| global-ordering.ll | ||
| global-visibility.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 | ||
| ldg-invariant.ll | ||
| ldparam-v4.ll | ||
| ldu-i8.ll | ||
| ldu-ldg.ll | ||
| ldu-reg-plus-offset.ll | ||
| lit.local.cfg | ||
| load-sext-i1.ll | ||
| load-with-non-coherent-cache.ll | ||
| LoadStoreVectorizer.ll | ||
| local-stack-frame.ll | ||
| loop-vectorize.ll | ||
| lower-aggr-copies.ll | ||
| lower-alloca.ll | ||
| lower-kernel-ptr-arg.ll | ||
| machine-sink.ll | ||
| MachineSink-call.ll | ||
| MachineSink-convergent.ll | ||
| managed.ll | ||
| math-intrins.ll | ||
| misaligned-vector-ldst.ll | ||
| module-inline-asm.ll | ||
| mulwide.ll | ||
| noduplicate-syncthreads.ll | ||
| nounroll.ll | ||
| nvcl-param-align.ll | ||
| nvvm-reflect-module-flag.ll | ||
| nvvm-reflect.ll | ||
| param-align.ll | ||
| pr13291-i1-store.ll | ||
| pr16278.ll | ||
| pr17529.ll | ||
| refl1.ll | ||
| reg-copy.ll | ||
| reg-types.ll | ||
| rotate.ll | ||
| rsqrt.ll | ||
| sched1.ll | ||
| sched2.ll | ||
| sext-in-reg.ll | ||
| sext-params.ll | ||
| shfl.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 | ||
| sm-version-60.ll | ||
| sm-version-61.ll | ||
| sm-version-62.ll | ||
| speculative-execution-divergent-target.ll | ||
| st-addrspace.ll | ||
| st-generic.ll | ||
| surf-read-cuda.ll | ||
| surf-read.ll | ||
| surf-write-cuda.ll | ||
| surf-write.ll | ||
| symbol-naming.ll | ||
| TailDuplication-convergent.ll | ||
| tex-read-cuda.ll | ||
| tex-read.ll | ||
| texsurf-queries.ll | ||
| tid-range.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-select.ll | ||
| vector-stores.ll | ||
| weak-global.ll | ||
| weak-linkage.ll | ||
| zero-cs.ll | ||
| zeroext-32bit.ll | ||