Sanjay Patel e6143904b9 revert r325515: [TTI CostModel] change default cost of FP ops to 1 (PR36280) ...

There are too many perf regressions resulting from this, so we need to 
investigate (and add tests for) targets like ARM and AArch64 before 
trying to reinstate.

llvm-svn: 325658

2018-02-21 01:42:52 +00:00

..

alternate-shuffle-cost.ll

…

arith-fp.ll

revert r325515: [TTI CostModel] change default cost of FP ops to 1 (PR36280)

2018-02-21 01:42:52 +00:00

arith.ll

[X86][SSE] Increase PMULLD costs to better match hardware

2018-02-10 19:27:10 +00:00

bitreverse.ll

[X86] Use mattr instead of mcpu in some of the cost model tests.

2017-12-18 07:21:58 +00:00

bswap.ll

…

cast.ll

[X86] Make v2i1 and v4i1 legal types without VLX

2018-01-07 18:20:37 +00:00

cmp.ll

…

costmodel.ll

[TargetTransformInfo] Check if function pointer is valid before calling isLoweredToCall

2017-10-04 20:14:08 +00:00

ctlz.ll

[X86] Use mattr instead of mcpu in some of the cost model tests.

2017-12-18 07:21:58 +00:00

ctpop.ll

[X86] Use mattr instead of mcpu in some of the cost model tests.

2017-12-18 07:21:58 +00:00

cttz.ll

[X86] Use mattr instead of mcpu in some of the cost model tests.

2017-12-18 07:21:58 +00:00

div.ll

[X86][AVX1] Account for cost of extract/insert of 256-bit SDIV/UDIV by mul sequences

2017-05-14 18:52:15 +00:00

fptosi.ll

[X86] Promote fp_to_sint v16f32->v16i16/v16i8 to avoid scalarization.

2017-11-29 00:32:09 +00:00

fptoui.ll

X86: Improve AVX512 fptoui lowering

2017-09-07 07:40:34 +00:00

gep.ll

Check for overflows when calculating the offset in GetGEPCost.

2017-09-27 23:16:56 +00:00

i32.ll

…

insert-extract-at-zero.ll

…

interleave-load-i32.ll

…

interleave-store-i32.ll

…

interleaved-load-float.ll

[LV][X86] update the cost of interleaving mem. access of floats

2017-11-06 10:56:20 +00:00

interleaved-load-i8.ll

[AVX512][AVX2]Cost calculation for interleave load/store patterns {v8i8,v16i8,v32i8,v64i8}

2017-10-18 11:41:55 +00:00

interleaved-load-store-double.ll

[TTI][X86] update costs of interleaved load\store of i64\double

2017-11-16 09:38:32 +00:00

interleaved-load-store-i64.ll

[TTI][X86] update costs of interleaved load\store of i64\double

2017-11-16 09:38:32 +00:00

interleaved-store-i8.ll

[AVX512][AVX2]Cost calculation for interleave load/store patterns {v8i8,v16i8,v32i8,v64i8}

2017-10-18 11:41:55 +00:00

intrinsic-cost.ll

revert r325515: [TTI CostModel] change default cost of FP ops to 1 (PR36280)

2018-02-21 01:42:52 +00:00

lit.local.cfg

…

load_store.ll

…

loop_v2.ll

…

masked-intrinsic-cost.ll

[LV][X86] Support of AVX2 Gathers code generation and update the LV with this

2017-11-20 08:18:12 +00:00

reduction.ll

revert r325515: [TTI CostModel] change default cost of FP ops to 1 (PR36280)

2018-02-21 01:42:52 +00:00

rem.ll

…

scalarize.ll

…

shuffle-broadcast.ll

[CostModel][X86] Add avx512vbmi broadcast/reverse/single-src shuffle cost tests

2017-08-10 17:33:25 +00:00

shuffle-reverse.ll

[CostModel][X86] Add avx512vbmi broadcast/reverse/single-src shuffle cost tests

2017-08-10 17:33:25 +00:00

shuffle-single-src.ll

[CostModel][X86][XOP] Improve costs for XOP shuffles

2017-08-16 13:50:20 +00:00

shuffle-two-src.ll

[CostModel][X86][XOP] Improve costs for XOP shuffles

2017-08-16 13:50:20 +00:00

sitofp.ll

…

slm-arith-costs.ll

[X86][CM] update add\sub costs of vectors of 64 in X86\SLM arch

2017-07-02 12:16:15 +00:00

sse-itoi.ll

…

strided-load-i8.ll

[AVX512][AVX2]Cost calculation for interleave load/store patterns {v8i8,v16i8,v32i8,v64i8}

2017-10-18 11:41:55 +00:00

strided-load-i16.ll

…

strided-load-i32.ll

…

strided-load-i64.ll

…

testshiftashr.ll

…

testshiftlshr.ll

…

testshiftshl.ll

…

tiny.ll

…

trunc.ll

[X86] Add AVX512 check lines to the cost model truncate test.

2017-10-03 03:47:34 +00:00

uitofp.ll

…

uniformshift.ll

…

vdiv-cost.ll

…

vector_gep.ll

Revert r314923: "Recommit : Use the basic cost if a GEP is not used as addressing mode"

2017-10-13 14:04:21 +00:00

vectorized-loop.ll

…

vselect-cost.ll

…

vshift-ashr-cost.ll

[X86][AVX1] Account for cost of extract/insert of 256-bit shifts

2017-05-14 20:52:11 +00:00

vshift-lshr-cost.ll

[X86][AVX1] Account for cost of extract/insert of 256-bit shifts

2017-05-14 20:52:11 +00:00

vshift-shl-cost.ll

[X86][SSE] Increase PMULLD costs to better match hardware

2018-02-10 19:27:10 +00:00