llvm-project/llvm/lib/Target/AMDGPU/SISchedule.td

106 lines
3.2 KiB
TableGen

//===-- SISchedule.td - SI Scheduling definitons -------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// MachineModel definitions for Southern Islands (SI)
//
//===----------------------------------------------------------------------===//
def WriteBranch : SchedWrite;
def WriteExport : SchedWrite;
def WriteLDS : SchedWrite;
def WriteSALU : SchedWrite;
def WriteSMEM : SchedWrite;
def WriteVMEM : SchedWrite;
def WriteBarrier : SchedWrite;
// Vector ALU instructions
def Write32Bit : SchedWrite;
def WriteQuarterRate32 : SchedWrite;
def WriteFullOrQuarterRate32 : SchedWrite;
def WriteFloatFMA : SchedWrite;
// Slow quarter rate f64 instruction.
def WriteDouble : SchedWrite;
// half rate f64 instruction (same as v_add_f64)
def WriteDoubleAdd : SchedWrite;
// Half rate 64-bit instructions.
def Write64Bit : SchedWrite;
// FIXME: Should there be a class for instructions which are VALU
// instructions and have VALU rates, but write to the SALU (i.e. VOPC
// instructions)
def SIFullSpeedModel : SchedMachineModel;
def SIQuarterSpeedModel : SchedMachineModel;
// BufferSize = 0 means the processors are in-order.
let BufferSize = 0 in {
// XXX: Are the resource counts correct?
def HWBranch : ProcResource<1>;
def HWExport : ProcResource<7>; // Taken from S_WAITCNT
def HWLGKM : ProcResource<31>; // Taken from S_WAITCNT
def HWSALU : ProcResource<1>;
def HWVMEM : ProcResource<15>; // Taken from S_WAITCNT
def HWVALU : ProcResource<1>;
}
class HWWriteRes<SchedWrite write, list<ProcResourceKind> resources,
int latency> : WriteRes<write, resources> {
let Latency = latency;
}
class HWVALUWriteRes<SchedWrite write, int latency> :
HWWriteRes<write, [HWVALU], latency>;
// The latency numbers are taken from AMD Accelerated Parallel Processing
// guide. They may not be accurate.
// The latency values are 1 / (operations / cycle) / 4.
multiclass SICommonWriteRes {
def : HWWriteRes<WriteBranch, [HWBranch], 100>; // XXX: Guessed ???
def : HWWriteRes<WriteExport, [HWExport], 100>; // XXX: Guessed ???
def : HWWriteRes<WriteLDS, [HWLGKM], 32>; // 2 - 64
def : HWWriteRes<WriteSALU, [HWSALU], 1>;
def : HWWriteRes<WriteSMEM, [HWLGKM], 10>; // XXX: Guessed ???
def : HWWriteRes<WriteVMEM, [HWVMEM], 450>; // 300 - 600
def : HWWriteRes<WriteBarrier, [HWBranch], 500>; // XXX: Guessed ???
def : HWVALUWriteRes<Write32Bit, 1>;
def : HWVALUWriteRes<Write64Bit, 2>;
def : HWVALUWriteRes<WriteQuarterRate32, 4>;
}
let SchedModel = SIFullSpeedModel in {
defm : SICommonWriteRes;
def : HWVALUWriteRes<WriteFloatFMA, 1>;
def : HWVALUWriteRes<WriteDouble, 4>;
def : HWVALUWriteRes<WriteDoubleAdd, 2>;
} // End SchedModel = SIFullSpeedModel
let SchedModel = SIQuarterSpeedModel in {
defm : SICommonWriteRes;
def : HWVALUWriteRes<WriteFloatFMA, 16>;
def : HWVALUWriteRes<WriteDouble, 16>;
def : HWVALUWriteRes<WriteDoubleAdd, 8>;
} // End SchedModel = SIQuarterSpeedModel