1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
llvm-mirror/lib
Simon Pilgrim b944c68941 [CostModel][X86] Improve f64/v2f64/v4f64 FMUL costs on AVX1 targets to account for slower btver2
BTVER2 has a weaker f64 multiplier that other AVX1-era targets, so we need to bump the worst case cost slightly - llvm-mca reports the new vectorization in simplebb is beneficial on btver2, bdver2 and sandybridge AVX1 targets
2021-05-21 18:12:13 +01:00
..
Analysis Move a definition into cpp from header in advance of other changes [nfc] 2021-05-21 09:18:04 -07:00
AsmParser [OpaquePtr] Make atomicrmw work with opaque pointers 2021-05-19 12:49:28 -07:00
BinaryFormat
Bitcode [IR][AutoUpgrade] Drop alignment from non-pointer parameters and returns 2021-05-20 09:54:38 -07:00
Bitstream
CodeGen AMDGPU/GlobalISel: Add subtarget to a test 2021-05-21 23:57:38 +09:00
DebugInfo Add support for DWARF embedded source to llvm-symbolizer. 2021-05-20 21:40:28 +04:00
Demangle [Demangle][Rust] Speculative fix for bot build failure 2021-05-19 00:40:24 +02:00
DWARFLinker
ExecutionEngine [RuntimeDyld] Add allowStubs/allowZeroSyms 2021-05-18 11:35:27 -07:00
Extensions
FileCheck
Frontend
Fuzzer
FuzzMutate
InterfaceStub
IR 3rd Reapply "[DebugInfo] Use variadic debug values to salvage BinOps and GEP instrs with non-const operands" 2021-05-21 11:06:20 +01:00
IRReader
LineEditor
Linker
LTO [SampleFDO] New hierarchical discriminator for Flow Sensitive SampleFDO 2021-05-18 16:23:43 -07:00
MC [AIX] Print printable byte list as quoted string 2021-05-21 02:37:55 +00:00
MCA
Object [WebAssembly] Fix PIC/GOT codegen for wasm64 2021-05-20 09:59:31 -07:00
ObjectYAML
Option
Passes Revert "[LoopUnrollAndJam] Change LoopUnrollAndJamPass to LoopNest pass" 2021-05-22 01:40:43 +09:00
ProfileData [CoverageMapping] Handle gaps in counter IDs for source-based coverage 2021-05-19 10:46:38 -07:00
Remarks
Support [APFloat] convertToDouble/Float can work on shorter types 2021-05-21 11:02:51 +07:00
TableGen
Target [CostModel][X86] Improve f64/v2f64/v4f64 FMUL costs on AVX1 targets to account for slower btver2 2021-05-21 18:12:13 +01:00
Testing
TextAPI
ToolDrivers
Transforms Revert "[LoopUnrollAndJam] Change LoopUnrollAndJamPass to LoopNest pass" 2021-05-22 01:40:43 +09:00
WindowsManifest
XRay
CMakeLists.txt