David Sherwood 7f498a865f [CostModel][LoopVectorize] Move some loop vectoriser tests (#113702) ...

Many tests that were in test/Analysis/CostModel were actually
loop vectoriser tests. I've moved them as follows:

Analysis/CostModel/X86 -> Transforms/LoopVectorize/X86/CostModel
Analysis/CostModel/AArch64/arith-fp-frem.ll ->
  Transforms/LoopVectorize/AArch64/arith-fp-frem-costs.ll

2024-10-30 13:50:02 +00:00

..

abs-codesize.ll

…

abs-latency.ll

…

abs-sizelatency.ll

[CostModel][X86] Adjust ABS scalar SizeLatency cost to 3uops

2024-06-11 10:29:18 +01:00

abs.ll

…

aggregates.ll

…

alternate-shuffle-cost.ll

…

arith-fix.ll

…

arith-fma.ll

…

arith-fp-codesize.ll

[CostModel][X86] Treat lrint/llrint as fptosi calls (#90883)

2024-05-03 18:06:50 +01:00

arith-fp-latency.ll

[CostModel][X86] Treat lrint/llrint as fptosi calls (#90883)

2024-05-03 18:06:50 +01:00

arith-fp-sizelatency.ll

[CostModel][X86] Treat lrint/llrint as fptosi calls (#90883)

2024-05-03 18:06:50 +01:00

arith-fp.ll

[CostModel][X86] Treat lrint/llrint as fptosi calls (#90883)

2024-05-03 18:06:50 +01:00

arith-int-codesize.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

arith-int-latency.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

arith-int-sizelatency.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

arith-int.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

arith-overflow.ll

[CostModel][X86] Add missing AVX512 vector mul overflow intrinsic costs

2024-07-29 15:53:42 +01:00

arith-sminmax-codesize.ll

…

arith-sminmax-latency.ll

…

arith-sminmax-sizelatency.ll

…

arith-sminmax.ll

…

arith-ssat-codesize.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

arith-ssat-latency.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

arith-ssat-sizelatency.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

arith-ssat.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

arith-uminmax-codesize.ll

…

arith-uminmax-latency.ll

…

arith-uminmax-sizelatency.ll

…

arith-uminmax.ll

…

arith-usat-codesize.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

arith-usat-latency.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

arith-usat-sizelatency.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

arith-usat.ll

[CostModel][X86] Add add/sat sat intrinsic costs

2024-07-25 14:35:39 +01:00

bitreverse-codesize.ll

[CostModel][X86] Update BITREVERSE costs for GFNI targets

2024-04-17 15:46:38 +01:00

bitreverse-latency.ll

[CostModel][X86] Update BITREVERSE costs for GFNI targets

2024-04-17 15:46:38 +01:00

bitreverse-sizelatency.ll

[CostModel][X86] Update BITREVERSE costs for GFNI targets

2024-04-17 15:46:38 +01:00

bitreverse.ll

[CostModel][X86] Update BITREVERSE costs for GFNI targets

2024-04-17 15:46:38 +01:00

bswap-codesize.ll

[CostModel][X86] Add explicit Silvermont test coverage for bswap costs

2024-01-02 11:21:32 +00:00

bswap-latency.ll

[CostModel][X86] Update SSSE3/AVX1 BSWAP costs

2024-01-02 12:06:48 +00:00

bswap-sizelatency.ll

[CostModel][X86] Add explicit Silvermont test coverage for bswap costs

2024-01-02 11:21:32 +00:00

bswap-store.ll

…

bswap.ll

[CostModel][X86] Update SSSE3/AVX1 BSWAP costs

2024-01-02 12:06:48 +00:00

cast.ll

[CostModel][X86] Update AVX1 sext v4i1 -> v4i64 cost based off worst case llvm-mca numbers

2024-04-04 17:17:55 +01:00

costmodel.ll

[CostModel][X86] Improve add/sub/mul overflow intrinsic costs

2024-07-25 16:01:05 +01:00

ctlz-codesize.ll

[X86] Allow speculative BSR/BSF instructions on targets with CMOV (#102885)

2024-08-22 11:11:00 +01:00

ctlz-latency.ll

[CostModel][X86] Add missing costkinds for scalar CTLZ/CTTZ instructions

2024-08-20 15:26:04 +01:00

ctlz-sizelatency.ll

[X86] Allow speculative BSR/BSF instructions on targets with CMOV (#102885)

2024-08-22 11:11:00 +01:00

ctlz.ll

[X86] Allow speculative BSR/BSF instructions on targets with CMOV (#102885)

2024-08-22 11:11:00 +01:00

ctpop-codesize.ll

[CostModel][X86] Fix expanded CTPOP i8 costs

2024-02-21 14:54:50 +00:00

ctpop-latency.ll

…

ctpop-sizelatency.ll

[CostModel][X86] Fix expanded CTPOP i8 costs

2024-02-21 14:54:50 +00:00

ctpop.ll

…

cttz-codesize.ll

[X86] Allow speculative BSR/BSF instructions on targets with CMOV (#102885)

2024-08-22 11:11:00 +01:00

cttz-latency.ll

[CostModel][X86] Add missing costkinds for scalar CTLZ/CTTZ instructions

2024-08-20 15:26:04 +01:00

cttz-sizelatency.ll

[X86] Allow speculative BSR/BSF instructions on targets with CMOV (#102885)

2024-08-22 11:11:00 +01:00

cttz.ll

[CostModel][X86] Add missing costkinds for scalar CTLZ/CTTZ instructions

2024-08-20 15:26:04 +01:00

div-codesize.ll

…

div-latency.ll

…

div-sizelatency.ll

…

div.ll

…

extend.ll

[CostModel][X86] Update AVX1 sext v4i1 -> v4i64 cost based off worst case llvm-mca numbers

2024-04-04 17:17:55 +01:00

fcmp-codesize.ll

…

fcmp-latency.ll

…

fcmp-sizelatency.ll

…

fcmp.ll

…

fmaxnum-codesize.ll

…

fmaxnum-latency.ll

…

fmaxnum-size-latency.ll

…

fmaxnum.ll

…

fminnum-codesize.ll

…

fminnum-latency.ll

…

fminnum-size-latency.ll

…

fminnum.ll

…

fptoi_sat.ll

TTI: Check legalization cost of fptosi_sat/fptoui_sat nodes (#100521)

2024-08-09 12:32:03 +04:00

fptosi.ll

…

fptoui.ll

…

free-intrinsics.ll

[DebugInfo][RemoveDIs] Final final test-maintenence patch (#80988)

2024-02-07 14:31:52 +00:00

fround.ll

…

fshl-codesize.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

fshl-latency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

fshl-sizelatency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

fshl.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

fshr-codesize.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

fshr-latency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

fshr-sizelatency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

fshr.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

gep.ll

…

i32.ll

…

icmp0.ll

[CostModel][X86] Reduce the extra costs for ICMP complex predicates when an operand is constant

2024-02-21 16:19:39 +00:00

icmp-codesize.ll

[TTI] Add cost model support for [u|s]cmp (#106824)

2024-08-31 21:25:04 +08:00

icmp-latency.ll

[TTI] Add cost model support for [u|s]cmp (#106824)

2024-08-31 21:25:04 +08:00

icmp-sizelatency.ll

[TTI] Add cost model support for [u|s]cmp (#106824)

2024-08-31 21:25:04 +08:00

icmp.ll

[TTI] Add cost model support for [u|s]cmp (#106824)

2024-08-31 21:25:04 +08:00

insert-extract-at-zero-inseltpoison.ll

…

insert-extract-at-zero.ll

…

intrinsic-cost-kinds.ll

[CostModel][X86] Add missing costkinds for scalar CTLZ/CTTZ instructions

2024-08-20 15:26:04 +01:00

intrinsic-cost.ll

…

lit.local.cfg

…

load_store.ll

…

load-broadcast.ll

[CostModel][X86] Broadcast shuffles can be free if they are from a one-use load

2024-04-23 11:11:15 +01:00

load-bswap.ll

…

load-to-trunc.ll

…

logicalop.ll

…

loop_v2-inseltpoison.ll

…

loop_v2.ll

…

masked-intrinsic-codesize.ll

[CostModel][X86] getGSVectorCost - add cost kind support

2024-05-08 16:24:39 +01:00

masked-intrinsic-cost-inseltpoison.ll

[TTI][X86] getGSScalarCost - don't bother with adding cost of ICMP for each i1 mask element

2024-05-11 13:37:48 +01:00

masked-intrinsic-cost.ll

[TTI][X86] getGSScalarCost - don't bother with adding cost of ICMP for each i1 mask element

2024-05-11 13:37:48 +01:00

masked-intrinsic-latency.ll

[CostModel][X86] getGSVectorCost - add cost kind support

2024-05-08 16:24:39 +01:00

masked-intrinsic-sizelatency.ll

[CostModel][X86] getGSVectorCost - add cost kind support

2024-05-08 16:24:39 +01:00

min-legal-vector-width.ll

…

mul32.ll

…

mul64.ll

…

mul-codesize.ll

…

mul-latency.ll

…

mul-sizelatency.ll

…

mul.ll

…

powi.ll

…

reduce-add.ll

…

reduce-and.ll

…

reduce-fadd.ll

…

reduce-fmax.ll

…

reduce-fmin.ll

…

reduce-fmul.ll

…

reduce-mul.ll

…

reduce-or.ll

…

reduce-smax.ll

…

reduce-smin.ll

…

reduce-umax.ll

…

reduce-umin.ll

…

reduce-xor.ll

…

reduction.ll

…

rem-codesize.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

rem-latency.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

rem-sizelatency.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

rem.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

scalarize.ll

…

select-codesize.ll

…

select-latency.ll

…

select-sizelatency.ll

…

select.ll

…

shuffle-broadcast-codesize.ll

…

shuffle-broadcast-fp16-codesize.ll

…

shuffle-broadcast-fp16-latency.ll

…

shuffle-broadcast-fp16-sizelatency.ll

…

shuffle-broadcast-fp16.ll

…

shuffle-broadcast-latency.ll

…

shuffle-broadcast-sizelatency.ll

…

shuffle-broadcast.ll

…

shuffle-concat_subvector-codesize.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-concat_subvector-latency.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-concat_subvector-sizelatency.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-concat_subvector.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-extract_subvector-codesize.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-extract_subvector-latency.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-extract_subvector-sizelatency.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-extract_subvector.ll

[CostModel] getInstructionCost - improve estimation of costs for length changing shuffles (#84156)

2024-03-07 10:46:27 +00:00

shuffle-insert_subvector-codesize.ll

…

shuffle-insert_subvector-latency.ll

…

shuffle-insert_subvector-sizelatency.ll

…

shuffle-insert_subvector.ll

…

shuffle-load-codesize.ll

…

shuffle-load-latency.ll

…

shuffle-load-sizelatency.ll

…

shuffle-load.ll

…

shuffle-non-pow-2-codesize.ll

…

shuffle-non-pow-2-latency.ll

…

shuffle-non-pow-2-sizelatency.ll

…

shuffle-non-pow-2.ll

…

shuffle-replication-i1-codesize.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i1-latency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i1-sizelatency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i1.ll

…

shuffle-replication-i8-codesize.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i8-latency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i8-sizelatency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i8.ll

…

shuffle-replication-i16-codesize.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i16-latency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i16-sizelatency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

shuffle-replication-i16.ll

…

shuffle-replication-i32-codesize.ll

…

shuffle-replication-i32-latency.ll

…

shuffle-replication-i32-sizelatency.ll

…

shuffle-replication-i32.ll

…

shuffle-replication-i64-codesize.ll

…

shuffle-replication-i64-latency.ll

…

shuffle-replication-i64-sizelatency.ll

…

shuffle-replication-i64.ll

…

shuffle-reverse-codesize.ll

…

shuffle-reverse-fp16-codesize.ll

…

shuffle-reverse-fp16-latency.ll

…

shuffle-reverse-fp16-sizelatency.ll

…

shuffle-reverse-fp16.ll

…

shuffle-reverse-latency.ll

…

shuffle-reverse-sizelatency.ll

…

shuffle-reverse.ll

…

shuffle-select-codesize.ll

…

shuffle-select-latency.ll

…

shuffle-select-sizelatency.ll

…

shuffle-select.ll

…

shuffle-single-src-codesize.ll

…

shuffle-single-src-fp16-codesize.ll

…

shuffle-single-src-fp16-latency.ll

…

shuffle-single-src-fp16-sizelatency.ll

…

shuffle-single-src-fp16.ll

…

shuffle-single-src-latency.ll

…

shuffle-single-src-sizelatency.ll

…

shuffle-single-src.ll

…

shuffle-splice-codesize.ll

…

shuffle-splice-latency.ll

…

shuffle-splice-sizelatency.ll

…

shuffle-splice.ll

…

shuffle-transpose-codesize.ll

…

shuffle-transpose-latency.ll

…

shuffle-transpose-sizelatency.ll

…

shuffle-transpose.ll

…

shuffle-two-src-codesize.ll

…

shuffle-two-src-fp16-codesize.ll

…

shuffle-two-src-fp16-latency.ll

…

shuffle-two-src-fp16-sizelatency.ll

…

shuffle-two-src-fp16.ll

…

shuffle-two-src-latency.ll

…

shuffle-two-src-sizelatency.ll

…

shuffle-two-src.ll

…

sitofp.ll

…

size-cost.ll

…

slm-arith-costs.ll

[X86] Lower vXi8 multiplies using PMADDUBSW on SSSE3+ targets (#95690)

2024-06-25 12:25:56 +01:00

sse-itoi.ll

…

tiny.ll

…

trunc-codesize.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

trunc-latency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

trunc-sizelatency.ll

[CostModel][X86] getCastInstrCost - improve CostKind adjustment when splitting src/dst types

2024-05-03 12:17:18 +01:00

trunc.ll

…

uitofp.ll

…

uniformshift-inseltpoison.ll

…

uniformshift.ll

…

vdiv-cost.ll

…

vector_gep-inseltpoison.ll

…

vector_gep.ll

…

vector-extract.ll

…

vector-insert-inseltpoison.ll

…

vector-insert-value.ll

…

vector-insert.ll

…

vectorized-loop.ll

…

vshift-ashr-codesize.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-ashr-cost-inseltpoison.ll

[CostModel][X86] Add basic GFNI target test coverage for shift/rotate costs

2024-04-17 18:35:17 +01:00

vshift-ashr-cost.ll

[CostModel][X86] Add basic GFNI target test coverage for shift/rotate costs

2024-04-17 18:35:17 +01:00

vshift-ashr-latency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-ashr-sizelatency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-lshr-codesize.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-lshr-cost-inseltpoison.ll

[CostModel][X86] Add basic GFNI target test coverage for shift/rotate costs

2024-04-17 18:35:17 +01:00

vshift-lshr-cost.ll

[CostModel][X86] Add basic GFNI target test coverage for shift/rotate costs

2024-04-17 18:35:17 +01:00

vshift-lshr-latency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-lshr-sizelatency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-shl-codesize.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-shl-cost-inseltpoison.ll

[CostModel][X86] Add basic GFNI target test coverage for shift/rotate costs

2024-04-17 18:35:17 +01:00

vshift-shl-cost.ll

[CostModel][X86] Add basic GFNI target test coverage for shift/rotate costs

2024-04-17 18:35:17 +01:00

vshift-shl-latency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00

vshift-shl-sizelatency.ll

[X86] Use GFNI for vXi8 shifts/rotates (#89115)

2024-05-07 10:28:55 +01:00