[AArch64] Adjust the cost model for Exynos M1 and M2

Fine tune the resources in a couple of ASIMD loads.

llvm-svn: 308904
This commit is contained in:
Evandro Menezes 2017-07-24 18:06:16 +00:00
parent 7052a6a505
commit 29ffb0e66a
1 changed files with 3 additions and 4 deletions

View File

@ -135,24 +135,20 @@ def : SchedAlias<WriteSTIdx, M1WriteSX>;
// FP data instructions.
def : WriteRes<WriteF, [M1UnitFADD]> { let Latency = 3; }
// TODO: FCCMP is much different.
def : WriteRes<WriteFCmp, [M1UnitNMISC]> { let Latency = 4; }
def : WriteRes<WriteFDiv, [M1UnitFVAR]> { let Latency = 15;
let ResourceCycles = [15]; }
def : WriteRes<WriteFMul, [M1UnitFMAC]> { let Latency = 4; }
// FP miscellaneous instructions.
// TODO: Conversion between register files is much different.
def : WriteRes<WriteFCvt, [M1UnitFCVT]> { let Latency = 3; }
def : WriteRes<WriteFImm, [M1UnitNALU]> { let Latency = 1; }
def : WriteRes<WriteFCopy, [M1UnitS]> { let Latency = 4; }
// FP load instructions.
// TODO: ASIMD loads are much different.
def : WriteRes<WriteVLD, [M1UnitL]> { let Latency = 5; }
// FP store instructions.
// TODO: ASIMD stores are much different.
def : WriteRes<WriteVST, [M1UnitS, M1UnitFST]> { let Latency = 1; }
// ASIMD FP instructions.
@ -216,6 +212,7 @@ def M1WriteFCVT3 : SchedWriteRes<[M1UnitFCVT]> { let Latency = 3; }
def M1WriteFCVT4 : SchedWriteRes<[M1UnitFCVT]> { let Latency = 4; }
def M1WriteFMAC4 : SchedWriteRes<[M1UnitFMAC]> { let Latency = 4; }
def M1WriteFMAC5 : SchedWriteRes<[M1UnitFMAC]> { let Latency = 5; }
// TODO
def M1WriteFVAR15 : SchedWriteRes<[M1UnitFVAR]> { let Latency = 15;
let ResourceCycles = [15]; }
def M1WriteFVAR23 : SchedWriteRes<[M1UnitFVAR]> { let Latency = 23;
@ -275,11 +272,13 @@ def M1WriteVLDK : SchedWriteRes<[M1UnitL,
def M1WriteVLDL : SchedWriteRes<[M1UnitL,
M1UnitNALU,
M1UnitNALU,
M1UnitL,
M1UnitNALU]> { let Latency = 7;
let ResourceCycles = [2]; }
def M1WriteVLDM : SchedWriteRes<[M1UnitL,
M1UnitNALU,
M1UnitNALU,
M1UnitL,
M1UnitNALU,
M1UnitNALU]> { let Latency = 7;
let ResourceCycles = [2]; }