Simon Pilgrim 90d25808c4 [CostModel][X86] Improve accuracy of sext/zext to 256-bit vector costs on AVX1 targets ...

Determined from llvm-mca analysis (btver2 vs bdver2 vs sandybridge), the split+extends+concat sequence on AVX1 capable targets are cheaper than the #ops that the cost was previously based on.

2021-05-27 18:17:50 +01:00

..

AArch64

[CostModel][AArch64] Add floating point arithmetic tests. NFC.

2021-05-26 20:26:20 +01:00

AMDGPU

[AMDGPU][CostModel] Refine cost model for control-flow instructions.

2021-04-10 09:20:24 +03:00

ARM

[InstructionCost] Don't conflate Invalid costs with Unknown costs.

2021-03-30 09:29:42 +01:00

PowerPC

[Cost]Canonicalize the cost for logical or/and reductions.

2021-03-19 11:01:58 -07:00

RISCV

[RISCV][NFC] Correct alignment in scatter/gather tests

2021-05-17 15:12:55 +01:00

SystemZ

Revert "[NFC] remove explicit default value for strboolattr attribute in tests"

2021-05-24 19:43:40 +02:00

X86

[CostModel][X86] Improve accuracy of sext/zext to 256-bit vector costs on AVX1 targets

2021-05-27 18:17:50 +01:00

free-intrinsics-datalayout.ll

[noalias.decl] Look through llvm.experimental.noalias.scope.decl

2021-01-19 20:09:42 +01:00

free-intrinsics-no_info.ll

[noalias.decl] Look through llvm.experimental.noalias.scope.decl

2021-01-19 20:09:42 +01:00

no_info.ll

…