llvm-6502/lib/Target/PowerPC/PPCScheduleP8.td
Hal Finkel 13141f04d3 [PowerPC] Fix the PPCInstrInfo::getInstrLatency implementation
PowerPC uses itineraries to describe processor pipelines (and dispatch-group
restrictions for P7/P8 cores). Unfortunately, the target-independent
implementation of TII.getInstrLatency calls ItinData->getStageLatency, and that
looks for the largest cycle count in the pipeline for any given instruction.
This, however, yields the wrong answer for the PPC itineraries, because we
don't encode the full pipeline. Because the functional units are fully
pipelined, we only model the initial stages (there are no relevant hazards in
the later stages to model), and so the technique employed by getStageLatency
does not really work. Instead, we should take the maximum output operand
latency, and that's what PPCInstrInfo::getInstrLatency now does.

This caused some test-case churn, including two unfortunate side effects.
First, the new arrangement of copies we get from function parameters now
sometimes blocks VSX FMA mutation (a FIXME has been added to the code and the
test cases), and we have one significant test-suite regression:

SingleSource/Benchmarks/BenchmarkGame/spectral-norm
	56.4185% +/- 18.9398%

In this benchmark we have a loop with a vectorized FP divide, and it with the
new scheduling both divides end up in the same dispatch group (which in this
case seems to cause a problem, although why is not exactly clear). The grouping
structure is hard to predict from the bottom of the loop, and there may not be
much we can do to fix this.

Very few other test-suite performance effects were really significant, but
almost all weakly favor this change. However, in light of the issues
highlighted above, I've left the old behavior available via a
command-line flag.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242188 91177308-0d34-0410-b5e6-96231b3b80d8
2015-07-14 20:02:02 +00:00

406 lines
23 KiB
TableGen

//===-- PPCScheduleP8.td - PPC P8 Scheduling Definitions ---*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the itinerary class data for the POWER8 processor.
//
//===----------------------------------------------------------------------===//
// Scheduling for the P8 involves tracking two types of resources:
// 1. The dispatch bundle slots
// 2. The functional unit resources
// Dispatch units:
def P8_DU1 : FuncUnit;
def P8_DU2 : FuncUnit;
def P8_DU3 : FuncUnit;
def P8_DU4 : FuncUnit;
def P8_DU5 : FuncUnit;
def P8_DU6 : FuncUnit;
def P8_DU7 : FuncUnit; // Only branch instructions will use DU7,DU8
def P8_DU8 : FuncUnit;
// 10 insns per cycle (2-LU, 2-LSU, 2-FXU, 2-FPU, 1-CRU, 1-BRU).
def P8_LU1 : FuncUnit; // Loads or fixed-point operations 1
def P8_LU2 : FuncUnit; // Loads or fixed-point operations 2
// Load/Store pipelines can handle Stores, fixed-point loads, and simple
// fixed-point operations.
def P8_LSU1 : FuncUnit; // Load/Store pipeline 1
def P8_LSU2 : FuncUnit; // Load/Store pipeline 2
// Fixed Point unit
def P8_FXU1 : FuncUnit; // FX pipeline 1
def P8_FXU2 : FuncUnit; // FX pipeline 2
// The Floating-Point Unit (FPU) and Vector Media Extension (VMX) units
// are combined on P7 and newer into a Vector Scalar Unit (VSU).
// The P8 Instruction latency documents still refers to the unit as the
// FPU, so keep in mind that FPU==VSU.
// In contrast to the P7, the VMX units on P8 are symmetric, so no need to
// split vector integer ops or 128-bit load/store/perms to the specific units.
def P8_FPU1 : FuncUnit; // VS pipeline 1
def P8_FPU2 : FuncUnit; // VS pipeline 2
def P8_CRU : FuncUnit; // CR unit (CR logicals and move-from-SPRs)
def P8_BRU : FuncUnit; // BR unit
def P8Itineraries : ProcessorItineraries<
[P8_DU1, P8_DU2, P8_DU3, P8_DU4, P8_DU5, P8_DU6, P8_DU7, P8_DU8,
P8_LU1, P8_LU2, P8_LSU1, P8_LSU2, P8_FXU1, P8_FXU2,
P8_FPU1, P8_FPU2, P8_CRU, P8_BRU], [], [
InstrItinData<IIC_IntSimple , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2,
P8_LU1, P8_LU2,
P8_LSU1, P8_LSU2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntGeneral , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2, P8_LU1,
P8_LU2, P8_LSU1, P8_LSU2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntISEL, [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2], 0>,
InstrStage<1, [P8_BRU]>],
[1, 1, 1, 1]>,
InstrItinData<IIC_IntCompare , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntDivW , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<15, [P8_FXU1, P8_FXU2]>],
[15, 1, 1]>,
InstrItinData<IIC_IntDivD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<23, [P8_FXU1, P8_FXU2]>],
[23, 1, 1]>,
InstrItinData<IIC_IntMulHW , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[4, 1, 1]>,
InstrItinData<IIC_IntMulHWU , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[4, 1, 1]>,
InstrItinData<IIC_IntMulLI , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[4, 1, 1]>,
InstrItinData<IIC_IntRotate , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntRotateD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntShift , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[1, 1, 1]>,
InstrItinData<IIC_IntTrapW , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[1, 1]>,
InstrItinData<IIC_IntTrapD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[1, 1]>,
InstrItinData<IIC_BrB , [InstrStage<1, [P8_DU7, P8_DU8], 0>,
InstrStage<1, [P8_BRU]>],
[3, 1, 1]>,
// FIXME - the Br* groups below are not branch related, so should probably
// be renamed.
// IIC_BrCR consists of the cr* instructions. (crand,crnor,creqv, etc).
// and should be 'First' in dispatch.
InstrItinData<IIC_BrCR , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_CRU]>],
[3, 1, 1]>,
// IIC_BrMCR consists of the mcrf instruction.
InstrItinData<IIC_BrMCR , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_CRU]>],
[3, 1, 1]>,
// IIC_BrMCRX consists of mcrxr (obsolete instruction) and mtcrf, which
// should be first in the dispatch group.
InstrItinData<IIC_BrMCRX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[3, 1, 1]>,
InstrItinData<IIC_BrMCRX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[3, 1]>,
InstrItinData<IIC_LdStLoad , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2]>],
[2, 1, 1]>,
InstrItinData<IIC_LdStLoadUpd , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2 ], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[2, 2, 1, 1]>,
// Update-Indexed form loads/stores are no longer first and last in the
// dispatch group. They are simply cracked, so require DU1,DU2.
InstrItinData<IIC_LdStLoadUpdX, [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2]>],
[2, 1, 1]>,
InstrItinData<IIC_LdStLDU , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[2, 2, 1, 1]>,
InstrItinData<IIC_LdStLDUX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLFD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LU1, P8_LU2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLVecX , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LU1, P8_LU2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLFDU , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLFDUX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[3, 3, 1, 1]>,
InstrItinData<IIC_LdStLHA , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2,
P8_LU1, P8_LU2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLHAU , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[4, 4, 1, 1]>,
// first+last in dispatch group.
InstrItinData<IIC_LdStLHAUX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_DU3], 0>,
InstrStage<1, [P8_DU4], 0>,
InstrStage<1, [P8_DU5], 0>,
InstrStage<1, [P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[4, 4, 1, 1]>,
InstrItinData<IIC_LdStLWA , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2]>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLWARX, [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_DU3], 0>,
InstrStage<1, [P8_DU4], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2]>],
[3, 1, 1]>,
// first+last
InstrItinData<IIC_LdStLDARX, [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_DU3], 0>,
InstrStage<1, [P8_DU4], 0>,
InstrStage<1, [P8_DU5], 0>,
InstrStage<1, [P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2]>],
[3, 1, 1]>,
InstrItinData<IIC_LdStLMW , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2,
P8_LU1, P8_LU2]>],
[2, 1, 1]>,
// Stores are dual-issued from the issue queue, so may only take up one
// dispatch slot. The instruction will be broken into two IOPS. The agen
// op is issued to the LSU, and the data op (register fetch) is issued
// to either the LU (GPR store) or the VSU (FPR store).
InstrItinData<IIC_LdStStore , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2]>,
InstrStage<1, [P8_LU1, P8_LU2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LU1, P8_LU2,
P8_LSU1, P8_LSU2]>]
[1, 1, 1]>,
InstrItinData<IIC_LdStSTDU , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LU1, P8_LU2,
P8_LSU1, P8_LSU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[2, 1, 1, 1]>,
// First+last
InstrItinData<IIC_LdStSTDUX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_DU3], 0>,
InstrStage<1, [P8_DU4], 0>,
InstrStage<1, [P8_DU5], 0>,
InstrStage<1, [P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[2, 1, 1, 1]>,
InstrItinData<IIC_LdStSTFD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTFDU , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[2, 1, 1, 1]>,
InstrItinData<IIC_LdStSTVEBX , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTDCX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_DU3], 0>,
InstrStage<1, [P8_DU4], 0>,
InstrStage<1, [P8_DU5], 0>,
InstrStage<1, [P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2], 0>,
InstrStage<1, [P8_LU1, P8_LU2]>],
[1, 1, 1]>,
InstrItinData<IIC_LdStSTWCX , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_DU2], 0>,
InstrStage<1, [P8_DU3], 0>,
InstrStage<1, [P8_DU4], 0>,
InstrStage<1, [P8_DU5], 0>,
InstrStage<1, [P8_DU6], 0>,
InstrStage<1, [P8_LSU1, P8_LSU2], 0>,
InstrStage<1, [P8_LU1, P8_LU2]>],
[1, 1, 1]>,
InstrItinData<IIC_SprMFCR , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_CRU]>],
[6, 1]>,
InstrItinData<IIC_SprMFCRF , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_CRU]>],
[3, 1]>,
InstrItinData<IIC_SprMTSPR , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FXU1, P8_FXU2]>],
[4, 1]>, // mtctr
InstrItinData<IIC_FPGeneral , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[5, 1, 1]>,
InstrItinData<IIC_FPAddSub , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[5, 1, 1]>,
InstrItinData<IIC_FPCompare , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[8, 1, 1]>,
InstrItinData<IIC_FPDivD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[33, 1, 1]>,
InstrItinData<IIC_FPDivS , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[27, 1, 1]>,
InstrItinData<IIC_FPSqrtD , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[44, 1, 1]>,
InstrItinData<IIC_FPSqrtS , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[32, 1, 1]>,
InstrItinData<IIC_FPFused , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[5, 1, 1, 1]>,
InstrItinData<IIC_FPRes , [InstrStage<1, [P8_DU1, P8_DU2, P8_DU3,
P8_DU4, P8_DU5, P8_DU6], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[5, 1, 1]>,
InstrItinData<IIC_VecGeneral , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[2, 1, 1]>,
InstrItinData<IIC_VecVSL , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[2, 1, 1]>,
InstrItinData<IIC_VecVSR , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[2, 1, 1]>,
InstrItinData<IIC_VecFP , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[6, 1, 1]>,
InstrItinData<IIC_VecFPCompare, [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[6, 1, 1]>,
InstrItinData<IIC_VecFPRound , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[6, 1, 1]>,
InstrItinData<IIC_VecComplex , [InstrStage<1, [P8_DU1], 0>,
InstrStage<1, [P8_FPU1, P8_FPU2]>],
[7, 1, 1]>,
InstrItinData<IIC_VecPerm , [InstrStage<1, [P8_DU1, P8_DU2], 0>,
InstrStage<1, [P8_FPU2, P8_FPU2]>],
[3, 1, 1]>
]>;
// ===---------------------------------------------------------------------===//
// P8 machine model for scheduling and other instruction cost heuristics.
// P8 has an 8 insn dispatch group (6 non-branch, 2 branch) and can issue up
// to 10 insns per cycle (2-LU, 2-LSU, 2-FXU, 2-FPU, 1-CRU, 1-BRU).
def P8Model : SchedMachineModel {
let IssueWidth = 8; // up to 8 instructions dispatched per cycle.
// up to six non-branch instructions.
// up to two branches in a dispatch group.
let MinLatency = 0; // Out-of-order dispatch.
let LoadLatency = 3; // Optimistic load latency assuming bypass.
// This is overriden by OperandCycles if the
// Itineraries are queried instead.
let MispredictPenalty = 16;
// Try to make sure we have at least 10 dispatch groups in a loop.
let LoopMicroOpBufferSize = 60;
let Itineraries = P8Itineraries;
}