maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

NEON/VFP stuff can be issued only via Pipe1 on A9 

llvm-svn: 105107
This commit is contained in:
Anton Korobeynikov 2010-05-29 19:25:29 +00:00
parent 94d7fd88fd
commit d4c7cceb70
1 changed files with 87 additions and 87 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

174
llvm/lib/Target/ARM/ARMScheduleA9.td
View File

@ -103,21 +103,21 @@ def CortexA9Itineraries : ProcessorItineraries<
// FP Special Register to Integer Register File Move
InstrItinData<IIC_fpSTAT , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>]>,
//
// Single-precision FP Unary
InstrItinData<IIC_fpUNA32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1]>,
//
// Double-precision FP Unary
InstrItinData<IIC_fpUNA64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1]>,
//
@ -125,124 +125,124 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_fpCMP32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 4 cycles
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1]>,
//
// Double-precision FP Compare
InstrItinData<IIC_fpCMP64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra latency cycles since wbck is 4 cycles
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1]>,
//
// Single to Double FP Convert
InstrItinData<IIC_fpCVTSD , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Double to Single FP Convert
InstrItinData<IIC_fpCVTDS , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Single to Half FP Convert
InstrItinData<IIC_fpCVTSH , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Half to Single FP Convert
InstrItinData<IIC_fpCVTHS , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [2, 1]>,
//
// Single-Precision FP to Integer Convert
InstrItinData<IIC_fpCVTSI , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Double-Precision FP to Integer Convert
InstrItinData<IIC_fpCVTDI , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Integer to Single-Precision FP Convert
InstrItinData<IIC_fpCVTIS , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Integer to Double-Precision FP Convert
InstrItinData<IIC_fpCVTID , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Single-precision FP ALU
InstrItinData<IIC_fpALU32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
//
// Double-precision FP ALU
InstrItinData<IIC_fpALU64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<5, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
//
// Single-precision FP Multiply
InstrItinData<IIC_fpMUL32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<6, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [5, 1, 1]>,
//
// Double-precision FP Multiply
InstrItinData<IIC_fpMUL64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<7, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [6, 1, 1]>,
//
// Single-precision FP MAC
InstrItinData<IIC_fpMAC32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<9, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [8, 0, 1, 1]>,
//
// Double-precision FP MAC
InstrItinData<IIC_fpMAC64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<10, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [9, 0, 1, 1]>,
//
// Single-precision FP DIV
InstrItinData<IIC_fpDIV32 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<16, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<10, [A9_NPipe]>], [15, 1, 1]>,
//
// Double-precision FP DIV
InstrItinData<IIC_fpDIV64 , [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<26, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<20, [A9_NPipe]>], [25, 1, 1]>,
//
// Single-precision FP SQRT
InstrItinData<IIC_fpSQRT32, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<18, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<13, [A9_NPipe]>], [17, 1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<13, [A9_NPipe]>], [17, 1]>,
//
// Double-precision FP SQRT
InstrItinData<IIC_fpSQRT64, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<33, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<28, [A9_NPipe]>], [32, 1]>,
//
@ -250,26 +250,26 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_fpMOVIS, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra 1 latency cycle since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1]>,
//
// Integer to Double-precision Move
InstrItinData<IIC_fpMOVID, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
// Extra 1 latency cycle since wbck is 2 cycles
InstrStage<3, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1, 1]>,
//
// Single-precision to Integer Move
InstrItinData<IIC_fpMOVSI, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1]>,
//
// Double-precision to Integer Move
InstrItinData<IIC_fpMOVDI, [InstrStage<1, [A9_DRegsVFP], 0, Required>,
InstrStage<2, [A9_DRegsN], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [1, 1, 1]>,
//
// Single-precision FP Load
@ -382,112 +382,112 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VUNAiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 2]>,
//
// Quad-register Integer Unary
InstrItinData<IIC_VUNAiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 2]>,
//
// Double-register Integer Q-Unary
InstrItinData<IIC_VQUNAiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Quad-register Integer CountQ-Unary
InstrItinData<IIC_VQUNAiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1]>,
//
// Double-register Integer Binary
InstrItinData<IIC_VBINiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3, 2, 2]>,
//
// Quad-register Integer Binary
InstrItinData<IIC_VBINiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3, 2, 2]>,
//
// Double-register Integer Subtract
InstrItinData<IIC_VSUBiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3, 2, 1]>,
//
// Quad-register Integer Subtract
InstrItinData<IIC_VSUBiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3, 2, 1]>,
//
// Double-register Integer Shift
InstrItinData<IIC_VSHLiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3, 1, 1]>,
//
// Quad-register Integer Shift
InstrItinData<IIC_VSHLiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3, 1, 1]>,
//
// Double-register Integer Shift (4 cycle)
InstrItinData<IIC_VSHLi4D, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
//
// Quad-register Integer Shift (4 cycle)
InstrItinData<IIC_VSHLi4Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 1, 1]>,
//
// Double-register Integer Binary (4 cycle)
InstrItinData<IIC_VBINi4D, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 2, 2]>,
//
// Quad-register Integer Binary (4 cycle)
InstrItinData<IIC_VBINi4Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 2, 2]>,
//
// Double-register Integer Subtract (4 cycle)
InstrItinData<IIC_VSUBiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 2, 1]>,
//
// Quad-register Integer Subtract (4 cycle)
InstrItinData<IIC_VSUBiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [4, 2, 1]>,
//
@ -495,7 +495,7 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VCNTiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3, 2, 2]>,
//
// Quad-register Integer Count
@ -504,35 +504,35 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VCNTiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [4, 2, 2]>,
//
// Double-register Absolute Difference and Accumulate
InstrItinData<IIC_VABAD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [6, 3, 2, 1]>,
//
// Quad-register Absolute Difference and Accumulate
InstrItinData<IIC_VABAQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [6, 3, 2, 1]>,
//
// Double-register Integer Pair Add Long
InstrItinData<IIC_VPALiD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [6, 3, 1]>,
//
// Quad-register Integer Pair Add Long
InstrItinData<IIC_VPALiQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [6, 3, 1]>,
//
@ -540,14 +540,14 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VMULi16D, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [6, 2, 2]>,
//
// Quad-register Integer Multiply (.8, .16)
InstrItinData<IIC_VMULi16Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [7, 2, 2]>,
//
@ -555,56 +555,56 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VMULi32D, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [7, 2, 1]>,
//
// Quad-register Integer Multiply (.32)
InstrItinData<IIC_VMULi32Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<4, [A9_NPipe]>], [9, 2, 1]>,
//
// Double-register Integer Multiply-Accumulate (.8, .16)
InstrItinData<IIC_VMACi16D, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [6, 3, 2, 2]>,
//
// Double-register Integer Multiply-Accumulate (.32)
InstrItinData<IIC_VMACi32D, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [7, 3, 2, 1]>,
//
// Quad-register Integer Multiply-Accumulate (.8, .16)
InstrItinData<IIC_VMACi16Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [7, 3, 2, 2]>,
//
// Quad-register Integer Multiply-Accumulate (.32)
InstrItinData<IIC_VMACi32Q, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<4, [A9_NPipe]>], [9, 3, 2, 1]>,
//
// Move Immediate
InstrItinData<IIC_VMOVImm, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [3]>,
//
// Double-register Permute Move
InstrItinData<IIC_VMOVD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// FIXME: all latencies are arbitrary, no information is available
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_LSPipe]>], [2, 1]>,
//
// Quad-register Permute Move
@ -613,42 +613,42 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VMOVQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// FIXME: all latencies are arbitrary, no information is available
InstrStage<4, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 1]>,
//
// Integer to Single-precision Move
InstrItinData<IIC_VMOVIS , [InstrStage<1, [A9_DRegsN], 0, Required>,
// FIXME: all latencies are arbitrary, no information is available
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [2, 1]>,
//
// Integer to Double-precision Move
InstrItinData<IIC_VMOVID , [InstrStage<1, [A9_DRegsN], 0, Required>,
// FIXME: all latencies are arbitrary, no information is available
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [2, 1, 1]>,
//
// Single-precision to Integer Move
InstrItinData<IIC_VMOVSI , [InstrStage<1, [A9_DRegsN], 0, Required>,
// FIXME: all latencies are arbitrary, no information is available
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [2, 1]>,
//
// Double-precision to Integer Move
InstrItinData<IIC_VMOVDI , [InstrStage<1, [A9_DRegsN], 0, Required>,
// FIXME: all latencies are arbitrary, no information is available
InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [2, 2, 1]>,
//
// Integer to Lane Move
InstrItinData<IIC_VMOVISL , [InstrStage<1, [A9_DRegsN], 0, Required>,
// FIXME: all latencies are arbitrary, no information is available
InstrStage<4, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 1, 1]>,
//
@ -656,7 +656,7 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VUNAD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [5, 2]>,
//
// Quad-register FP Unary
@ -665,7 +665,7 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VUNAQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [6, 2]>,
//
// Double-register FP Binary
@ -674,7 +674,7 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VBIND, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [5, 2, 2]>,
//
// Quad-register FP Binary
@ -685,14 +685,14 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VBINQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [6, 2, 2]>,
//
// Double-register FP Multiple-Accumulate
InstrItinData<IIC_VMACD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [6, 3, 2, 1]>,
//
// Quad-register FP Multiple-Accumulate
@ -701,28 +701,28 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VMACQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<4, [A9_NPipe]>], [8, 4, 2, 1]>,
//
// Double-register Reciprical Step
InstrItinData<IIC_VRECSD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [6, 2, 2]>,
//
// Quad-register Reciprical Step
InstrItinData<IIC_VRECSQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<10, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<4, [A9_NPipe]>], [8, 2, 2]>,
//
// Double-register Permute
InstrItinData<IIC_VPERMD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 6 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [2, 2, 1, 1]>,
//
// Quad-register Permute
@ -731,7 +731,7 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VPERMQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 3, 1, 1]>,
//
// Quad-register Permute (3 cycle issue)
@ -740,7 +740,7 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VPERMQ3, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<3, [A9_LSPipe]>], [4, 4, 1, 1]>,
//
@ -748,57 +748,57 @@ def CortexA9Itineraries : ProcessorItineraries<
InstrItinData<IIC_VEXTD, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<1, [A9_NPipe]>], [2, 1, 1]>,
//
// Quad-register VEXT
InstrItinData<IIC_VEXTQ, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 9 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 1, 1]>,
//
// VTB
InstrItinData<IIC_VTB1, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 2, 1]>,
InstrItinData<IIC_VTB2, [InstrStage<2, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 2, 2, 1]>,
InstrItinData<IIC_VTB3, [InstrStage<2, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<3, [A9_NPipe]>], [4, 2, 2, 3, 1]>,
InstrItinData<IIC_VTB4, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<3, [A9_NPipe]>], [4, 2, 2, 3, 3, 1]>,
//
// VTBX
InstrItinData<IIC_VTBX1, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 1, 2, 1]>,
InstrItinData<IIC_VTBX2, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 7 cycles
InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [3, 1, 2, 2, 1]>,
InstrItinData<IIC_VTBX3, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<3, [A9_NPipe]>], [4, 1, 2, 2, 3, 1]>,
InstrItinData<IIC_VTBX4, [InstrStage<1, [A9_DRegsN], 0, Required>,
// Extra latency cycles since wbck is 8 cycles
InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
InstrStage<1, [A9_Pipe0, A9_Pipe1]>,
InstrStage<1, [A9_Pipe1]>,
InstrStage<2, [A9_NPipe]>], [4, 1, 2, 2, 3, 3, 1]>
]>;