RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2025-02-28 00:50:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix A8 FP NEON MAC itins

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@100666 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Anton Korobeynikov 2010-04-07 18:21:33 +00:00
parent 924369d58e
commit f3da92b2f2
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Target/ARM/ARMScheduleV7.td
View File

@ -423,13 +423,13 @@ def CortexA8Itineraries : ProcessorItineraries<[
//
// Double-register FP Multiple-Accumulate
InstrItinData<IIC_VMACD, [InstrStage<1, [FU_Pipe0, FU_Pipe1]>,
InstrStage<1, [FU_NPipe]>], [9, 2, 2, 3]>,
InstrStage<1, [FU_NPipe]>], [9, 3, 2, 2]>,
//
// Quad-register FP Multiple-Accumulate
// Result written in N9, but that is relative to the last cycle of multicycle,
// so we use 10 for those cases
InstrItinData<IIC_VMACQ, [InstrStage<1, [FU_Pipe0, FU_Pipe1]>,
InstrStage<2, [FU_NPipe]>], [10, 2, 2, 3]>,
InstrStage<2, [FU_NPipe]>], [10, 3, 2, 2]>,
//
// Double-register Reciprical Step
InstrItinData<IIC_VRECSD, [InstrStage<1, [FU_Pipe0, FU_Pipe1]>,