Justin Lebar 6f09ea3f57 [NVPTX] Compute approx sqrt as 1/rsqrt(x) rather than x*rsqrt(x). ...

x*rsqrt(x) returns NaN for x == 0, whereas 1/rsqrt(x) returns 0, as
desired.

Verified that the particular nvptx approximate instructions here do in
fact return 0 for x = 0.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293713 91177308-0d34-0410-b5e6-96231b3b80d8

2017-01-31 23:08:57 +00:00

..

access-non-generic.ll

NVPTX: Move InferAddressSpaces to generic code

2017-01-31 01:10:58 +00:00

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

[NVPTX] Implement min/max in tablegen, rather than with custom DAGComine logic.

2017-01-18 00:09:01 +00:00

compare-int.ll

…

constant-vectors.ll

…

convergent-mir-call.ll

…

convert-fp.ll

[NVPTX] Add fptosi tests to convert-fp.ll.

2017-01-15 16:55:54 +00:00

convert-int-sm20.ll

…

ctlz.ll

[NVPTX] Fix function names in ctlz.ll test. Test-only change.

2017-01-18 00:07:52 +00:00

ctpop.ll

…

cttz.ll

…

debug-file-loc.ll

…

disable-opt.ll

…

div-ri.ll

…

divrem-combine.ll

…

envreg.ll

…

extloadv.ll

…

f16-instructions.ll

[NVPTX] Fix lowering of fp16 ISD::FNEG.

2017-01-19 00:14:45 +00:00

fast-math.ll

[NVPTX] Compute approx sqrt as 1/rsqrt(x) rather than x*rsqrt(x).

2017-01-31 23:08:57 +00:00

fcos-no-fast-math.ll

[NVPTX] Only lower sin/cos to approximate instructions if unsafe math is allowed.

2017-01-13 18:48:13 +00:00

fma-assoc.ll

[DAGCombine] require UnsafeFPMath for re-association of addition

2017-01-31 14:35:37 +00:00

fma-disable.ll

…

fma.ll

…

fp16.ll

…

fp-contract.ll

…

fp-literals.ll

…

fsin-no-fast-math.ll

[NVPTX] Only lower sin/cos to approximate instructions if unsafe math is allowed.

2017-01-13 18:48:13 +00:00

function-align.ll

…

generic-to-nvvm-ir.ll

[IR] Remove the DIExpression field from DIGlobalVariable.

2016-12-20 02:09:43 +00:00

generic-to-nvvm.ll

…

global-addrspace.ll

…

global-ctor-empty.ll

…

global-ctor.ll

…

global-dtor.ll

…

global-ordering.ll

…

global-variable-big.ll

[NVPTX] Support global variables of integer type larger than i64.

2017-01-18 00:29:53 +00:00

global-visibility.ll

…

globals_init.ll

…

globals_lowering.ll

…

gvar-init.ll

…

half.ll

[NVPTX] Added support for half-precision floating point.

2017-01-13 20:56:17 +00:00

i1-global.ll

…

i1-int-to-fp.ll

…

i1-param.ll

…

i8-param.ll

…

idioms.ll

[NVPTX] Lower integer absolute value idiom to abs instruction.

2017-01-18 00:08:44 +00:00

imad.ll

…

implicit-def.ll

…

inline-asm.ll

…

intrin-nocapture.ll

…

intrinsic-old.ll

[NVVMIntrRange] Only set range metadata if none is already present

2016-12-22 00:51:59 +00:00

intrinsics.ll

Fix some broken CHECK lines.

2017-01-22 20:28:56 +00:00

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

NVPTX: Move InferAddressSpaces to generic code

2017-01-31 01:10:58 +00:00

lower-kernel-ptr-arg.ll

…

machine-sink.ll

…

MachineSink-call.ll

…

MachineSink-convergent.ll

…

managed.ll

…

math-intrins.ll

[NVPTX] Add codegen tests for llvm.fma.

2017-01-15 16:55:37 +00:00

misaligned-vector-ldst.ll

…

module-inline-asm.ll

…

mulwide.ll

…

named-barriers.ll

[NVPTX] Add intrinsics to support named barriers.

2017-01-28 16:38:15 +00:00

noduplicate-syncthreads.ll

…

nounroll.ll

…

nvcl-param-align.ll

…

nvvm-reflect-module-flag.ll

…

nvvm-reflect.ll

[NVPTX] Let there be One True Way to set NVVMReflect params.

2017-01-15 16:54:35 +00:00

param-align.ll

…

pr13291-i1-store.ll

…

pr16278.ll

…

pr17529.ll

…

refl1.ll

…

reg-copy.ll

…

reg-types.ll

…

rotate.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

…

sqrt-approx.ll

[NVPTX] Compute approx sqrt as 1/rsqrt(x) rather than x*rsqrt(x).

2017-01-31 23:08:57 +00:00

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

[SelectionDAG] Correctly transform range metadata to AssertZExt

2017-01-06 00:11:46 +00:00

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

…