[clang] [llvm] [AArch64] Add support for Qualcomm Oryon processor (PR #91022)
Eli Friedman via llvm-commits
llvm-commits at lists.llvm.org
Wed May 29 10:34:01 PDT 2024
================
@@ -0,0 +1,1659 @@
+//=- AArch64SchedOryon.td - Qualcomm Oryon CPU 001 ---*- tablegen -*-=//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the scheduling model for Qualcomm Oryon
+// family of processors.
+//
+//===----------------------------------------------------------------------===//
+
+//===----------------------------------------------------------------------===//
+// Pipeline Description.
+
+def OryonModel : SchedMachineModel {
+ let IssueWidth = 14;
+ let MicroOpBufferSize = 376;
+ let LoadLatency = 4;
+ let MispredictPenalty = 13; // 13 cycles for mispredicted branch.
+ let LoopMicroOpBufferSize = 0; // Do not have a LoopMicroOpBuffer
+ let PostRAScheduler = 1; // Using PostRA sched.
+ let CompleteModel = 1;
+
+ list<Predicate> UnsupportedFeatures = !listconcat(SVEUnsupported.F,
+ SMEUnsupported.F,
+ MTEUnsupported.F,
+ PAUnsupported.F,
+ [HasPAuth, HasCSSC]);
+}
+
+let SchedModel = OryonModel in {
+
+// Issue ports.
+// IXU has 6 ports p0 ~ p5
+// LSU has 4 ports p6 ~ p9(ls0 ~ ls3), p10/p11(std0, std1) has to work with ls0~ls3
+// VXU has 4 ports p12 ~ p15
+
+// cross IXU/LSU/VXU resource group for FMOV P41 of VXU
+// I2V
+def ORYONI4FP0 : ProcResource<1>;
+def ORYONI5FP1 : ProcResource<1>;
+// V2I
+def ORYONFP0I4 : ProcResource<1>;
+def ORYONFP1I5 : ProcResource<1>;
+
+// store 1 for normal store instructions
+def ORYONST0 : ProcResource<1>;
+// store 2 for normal store instructions
+def ORYONST1 : ProcResource<1>;
+
+// Port 0: ALU/Indirect/Direct Branch.
+def ORYONP0 : ProcResource<1>;
+
+// Port 1: ALU/Direct Branch.
+def ORYONP1 : ProcResource<1>;
+
+// Port 2: ALU.
+def ORYONP2 : ProcResource<1>;
+
+// Port 3: ALU.
+def ORYONP3 : ProcResource<1>;
+
+// Port 4: ALU.
+def ORYONP4 : ProcResource<1> {
+ let Super = ORYONI4FP0;
+ let Super = ORYONFP0I4; }
+
+// Port 5: ALU.
+def ORYONP5 : ProcResource<1> {
+ let Super = ORYONI5FP1;
+ let Super = ORYONFP1I5; }
+
+// Port 6: Load/Store. LS0
+def ORYONP6 : ProcResource<1> {
+ let Super = ORYONST0; }
+
+// Port 7: Load/store. LS1
+def ORYONP7 : ProcResource<1> {
+ let Super = ORYONST0; }
+
+// Port 8: Load/Store. LS2
+def ORYONP8 : ProcResource<1> {
+ let Super = ORYONST1; }
+
+// Port 9: Load/store. LS3
+def ORYONP9 : ProcResource<1> {
+ let Super = ORYONST1; }
+
+// Port 10: Load/Store. STD0
+def ORYONP10SD0 : ProcResource<1> {
+ let Super = ORYONST0; }
+
+// Port 11: Load/store. STD1
+def ORYONP11SD1 : ProcResource<1> {
+ let Super = ORYONST1; }
+
+// Port 12: FP/Neon/SIMD/Crypto.
+def ORYONP12FP0 : ProcResource<1> {
+ let Super = ORYONI4FP0;
+ let Super = ORYONFP0I4; }
+
+// Port 13: FP/Neon/SIMD/Crypto.
+def ORYONP13FP1 : ProcResource<1> {
+ let Super = ORYONI5FP1;
+ let Super = ORYONFP1I5; }
+
+// Port 14: FP/Neon/SIMD/Crypto.
+def ORYONP14FP2 : ProcResource<1>;
+
+// Port 15: FP/Neon/SIMD/Crypto.
+def ORYONP15FP3 : ProcResource<1>;
+
+// Define groups for the functional units on each issue port. Each group
+// created will be used by a WriteRes.
+
+// Integer add/shift/logical/misc. instructions on port I0/I1/I2/I3/I4/I5.
+def ORYONI012345 : ProcResGroup<[ORYONP0, ORYONP1, ORYONP2,
+ ORYONP3, ORYONP4, ORYONP5]> {
+ let BufferSize = 120;
+}
+
+// Direct Conditional Branch instructions on ports I0/I1.
+def ORYONI01 : ProcResGroup<[ORYONP0, ORYONP1]> {
+ let BufferSize = 40;
+}
+
+// Indirect/crypto Conditional Branch instructions on ports I0.
+def ORYONI0 : ProcResGroup<[ORYONP0]> {
+ let BufferSize = 20;
+}
+
+// Crypto/CRC/PAU instructions on ports I2.
+def ORYONI2 : ProcResGroup<[ORYONP2]> {
+ let BufferSize = 20;
+}
+
+// Multiply/Multiply-ADD instructions on ports I4/I5.
+def ORYONI45 : ProcResGroup<[ORYONP4, ORYONP5]> {
+ let BufferSize = 40;
+}
+
+// Divide instructions on ports I5.
+def ORYONI5 : ProcResGroup<[ORYONP5]> {
+ let BufferSize = 20;
+}
+
+// Comparison instructions on ports I0/I1/I2/I3.
+def ORYONI0123 : ProcResGroup<[ORYONP0, ORYONP1,
+ ORYONP2, ORYONP3]> {
+ let BufferSize = 80;
+}
+
+// Load instructions on ports P6/P7/P8/P9.
+def ORYONLD : ProcResGroup<[ORYONP6, ORYONP7, ORYONP8, ORYONP9]> {
+ let BufferSize = 64;
+}
+
+// Store instructions on combo of STA/STD pipes
+def ORYONST : ProcResGroup<[ORYONST0, ORYONST1]> {
+ let BufferSize = 64;
+}
+
+// Arithmetic and CRYP-AED ASIMD/FP instructions on ports FP0/FP1/FP2/FP3.
+def ORYONFP0123 : ProcResGroup<[ORYONP12FP0, ORYONP13FP1,
+ ORYONP14FP2, ORYONP15FP3]> {
+ let BufferSize = 192;
+}
+
+// FP Comparison and F/I move instructions on ports FP0/FP1.
+def ORYONFP01 : ProcResGroup<[ORYONP12FP0, ORYONP13FP1]> {
+ let BufferSize = 96;
+}
+
+// FDIV instructions on ports FP3.
+def ORYONFP3 : ProcResGroup<[ORYONP15FP3]> {
+ let BufferSize = 48;
+}
+
+// CRYP-SHA instructions on ports FP1.
+def ORYONFP1 : ProcResGroup<[ORYONP14FP2]> {
+ let BufferSize = 48;
+}
+
+def ORYONFP2 : ProcResGroup<[ORYONP14FP2]> {
+ let BufferSize = 48;
+}
+
+// Reciprocal, Squre root on FP0.
+def ORYONFP0 : ProcResGroup<[ORYONP12FP0]> {
+ let BufferSize = 48;
+}
+
+// cross IXU/LSU/VXU resource group for FMOV P41 of VXU
+// I2V
+def ORYONI2V : ProcResGroup<[ORYONI4FP0, ORYONI5FP1]> {
+ let BufferSize = 40;
+}
+
+// V2I
+def ORYONV2I : ProcResGroup<[ORYONFP0I4, ORYONFP1I5]> {
+ let BufferSize = 96;
+}
+
+// Define commonly used write types for InstRW specializations.
+// All definitions follow the format: ORYONWrite_<NumCycles>Cyc_<Resources>.
+
+// Because of the complexity of Oryon CPU, we skip the following
+// generic definitions and define each instruction specifically
+
+// These WriteRes entries are not used in the Falkor sched model.
+def : WriteRes<WriteImm, []> { let Unsupported = 1; }
+def : WriteRes<WriteI, []> { let Unsupported = 1; }
+def : WriteRes<WriteISReg, []> { let Unsupported = 1; }
+def : WriteRes<WriteIEReg, []> { let Unsupported = 1; }
+def : WriteRes<WriteExtr, []> { let Unsupported = 1; }
+def : WriteRes<WriteIS, []> { let Unsupported = 1; }
+def : WriteRes<WriteID32, []> { let Unsupported = 1; }
+def : WriteRes<WriteID64, []> { let Unsupported = 1; }
+def : WriteRes<WriteIM32, []> { let Unsupported = 1; }
+def : WriteRes<WriteIM64, []> { let Unsupported = 1; }
+def : WriteRes<WriteBr, []> { let Unsupported = 1; }
+def : WriteRes<WriteBrReg, []> { let Unsupported = 1; }
+def : WriteRes<WriteLD, []> { let Unsupported = 1; }
+def : WriteRes<WriteST, []> { let Unsupported = 1; }
+def : WriteRes<WriteSTP, []> { let Unsupported = 1; }
+def : WriteRes<WriteAdr, []> { let Unsupported = 1; }
+def : WriteRes<WriteLDIdx, []> { let Unsupported = 1; }
+def : WriteRes<WriteSTIdx, []> { let Unsupported = 1; }
+def : WriteRes<WriteF, []> { let Unsupported = 1; }
+def : WriteRes<WriteFCmp, []> { let Unsupported = 1; }
+def : WriteRes<WriteFCvt, []> { let Unsupported = 1; }
+def : WriteRes<WriteFCopy, []> { let Unsupported = 1; }
+def : WriteRes<WriteFImm, []> { let Unsupported = 1; }
+def : WriteRes<WriteFMul, []> { let Unsupported = 1; }
+def : WriteRes<WriteFDiv, []> { let Unsupported = 1; }
+def : WriteRes<WriteVd, []> { let Unsupported = 1; }
+def : WriteRes<WriteVq, []> { let Unsupported = 1; }
+def : WriteRes<WriteVLD, []> { let Unsupported = 1; }
+def : WriteRes<WriteVST, []> { let Unsupported = 1; }
+def : WriteRes<WriteSys, []> { let Unsupported = 1; }
+def : WriteRes<WriteBarrier, []> { let Unsupported = 1; }
+def : WriteRes<WriteHint, []> { let Unsupported = 1; }
+def : WriteRes<WriteLDHi, []> { let Unsupported = 1; }
+def : WriteRes<WriteAtomic, []> { let Unsupported = 1; }
+
+// These ReadAdvance entries will be defined in later implementation
+def : ReadAdvance<ReadI, 0>;
+def : ReadAdvance<ReadISReg, 0>;
+def : ReadAdvance<ReadIEReg, 0>;
+def : ReadAdvance<ReadIM, 0>;
+def : ReadAdvance<ReadIMA, 0>;
+def : ReadAdvance<ReadID, 0>;
+def : ReadAdvance<ReadExtrHi, 0>;
+def : ReadAdvance<ReadAdrBase, 0>;
+def : ReadAdvance<ReadVLD, 0>;
+def : ReadAdvance<ReadST, 0>;
+
+
+//IXU resource definition
+// 1 cycles NO pipe
+def ORYONWrite_1Cyc_NONE : SchedWriteRes<[]>;
+
+// 1 cycles on I01.
+def ORYONWrite_1Cyc_I01 : SchedWriteRes<[ORYONI01]>;
+
+def ORYONWrite_1Cyc_2Uops_I01 : SchedWriteRes<[ORYONI01]> {
+ let NumMicroOps = 2;
+}
+
+def ORYONWrite_1Cyc_I0 : SchedWriteRes<[ORYONI0]>;
+
+// 7 cycles on I2. PAC*/AUT* instructions
+def ORYONWrite_7Cyc_I2 : SchedWriteRes<[ORYONI2]> {
+ let Latency = 7;
+}
+
+// 7 cycles on I2. PAC*/AUT* instructions
+def ORYONWrite_7Cyc_3Uops_I2 : SchedWriteRes<[ORYONI2]> {
+ let Latency = 7;
+ let NumMicroOps = 3;
+}
+
+// 9 (7+1+1) cycles on I2 and I0/I1, I0. Authentication branch instructions
+// these instructions are broken down to three uops
+// a. PtrAuth on pipe 2 taking 7 cycles
+// b. Link Register Update on pipes 0 and 1 taking 1 cycle
+// c. Indirect branch on pipe 0 taking 1 cycle
+
+def ORYONWrite_9Cyc_I012 : SchedWriteRes<[ORYONI2, ORYONI01]> {
+ let Latency = 9;
+ let NumMicroOps = 3;
+}
+
+// 3 cycles on I2. CRC32 and CRC32C instructions
+def ORYONWrite_3Cyc_I2 : SchedWriteRes<[ORYONI2]> {
+ let Latency = 3;
+}
+
+// 1 cycle on I012345
+def ORYONWrite_1Cyc_I012345 : SchedWriteRes<[ORYONI012345]>;
+
+// 1 cycle on I0123
+def ORYONWrite_1Cyc_I0123 : SchedWriteRes<[ORYONI0123]>;
+
+// 1 cycle on 2 of I012345
+def ORYONWrite_1Cyc_I012345_I012345 :
+SchedWriteRes<[ORYONI012345, ORYONI012345]> ;
+
+// 2 cycle on 2 of I0123 with ReleaseAtCycles
+def ORYONWrite_2Cyc_I0123_I0123_RC :
+SchedWriteRes<[ORYONI0123, ORYONI0123]> {
+ let Latency = 2;
+ let ReleaseAtCycles = [2,2];
+}
+
+// 2 cycle on 2 of I012345
+def ORYONWrite_2Cyc_I012345_I012345_RC :
+SchedWriteRes<[ORYONI012345, ORYONI012345]> {
+ let Latency = 2;
+ let ReleaseAtCycles = [2,2];
+}
+
+// 3 cycle on 2 of I45
+def ORYONWrite_3Cyc_I45_I45_RC :
+SchedWriteRes<[ORYONI45, ORYONI45]> {
+ let Latency = 3;
+ let ReleaseAtCycles = [2,2];
+}
+
+// 3 cycle on I45
+def ORYONWrite_3Cyc_I45 : SchedWriteRes<[ORYONI45]> {
+ let Latency = 3;
+}
+
+// 7 cycle on I2 32-bit integer division
+def ORYONWrite_7Cyc_I2_RC : SchedWriteRes<[ORYONI2]> {
+ let Latency = 7;
+ let ReleaseAtCycles = [2];
+}
+
+// 9 cycle on I2 64-bit integer division
+def ORYONWrite_9Cyc_I2_RC : SchedWriteRes<[ORYONI2]> {
+ let Latency = 9;
+ let ReleaseAtCycles = [2];
+}
+
+// LSU resource definition
+// need to define WriteLDAdr, WriteAdrAdr, WriteLDHi, WriteSTX
+// 4 cycle on LS(P6789)
+def ORYONWrite_4Cyc_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 4;
+}
+
+// 4 cycle for Post/Pre inc/dec access, also covers all pair loads Post/Pre
+def ORYONWrite_4Cyc_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 4;
+}
+
+// 5 (4+1) for VXU SIMD access/could also include FP
+// resource might not be correct, as VXU resource not included
+def ORYONWrite_5Cyc_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+}
+
+def ORYONWrite_5Cyc_2Uops_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+ let NumMicroOps = 2;
+}
+
+def ORYONWrite_5Cyc_3Uops_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+ let NumMicroOps = 3;
+}
+
+def ORYONWrite_5Cyc_4Uops_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+ let NumMicroOps = 4;
+}
+
+def ORYONWrite_5Cyc_5Uops_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+ let NumMicroOps = 5;
+}
+
+def ORYONWrite_5Cyc_6Uops_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+ let NumMicroOps = 6;
+}
+
+def ORYONWrite_5Cyc_8Uops_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+ let NumMicroOps = 8;
+}
+
+def ORYONWrite_5Cyc_10Uops_LD : SchedWriteRes<[ORYONLD]> {
+ let Latency = 5;
+ let NumMicroOps = 10;
+}
+
+// 6 cycle for Post/Pre inc/dec access
+def ORYONWrite_5Cyc_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+}
+
+def ORYONWrite_5Cyc_2Uops_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+ let NumMicroOps = 2;
+}
+
+def ORYONWrite_5Cyc_3Uops_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+ let NumMicroOps = 3;
+}
+
+def ORYONWrite_5Cyc_4Uops_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+ let NumMicroOps = 4;
+}
+
+def ORYONWrite_5Cyc_5Uops_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+ let NumMicroOps = 5;
+}
+
+def ORYONWrite_5Cyc_6Uops_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+ let NumMicroOps = 6;
+}
+
+def ORYONWrite_5Cyc_8Uops_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+ let NumMicroOps = 8;
+}
+
+def ORYONWrite_5Cyc_10Uops_LD_I012345 : SchedWriteRes<[ORYONLD, ORYONI012345]> {
+ let Latency = 5;
+ let NumMicroOps = 10;
+}
+
+// 1 cycle for all generic stores
+def ORYONWrite_1Cyc_ST : SchedWriteRes<[ORYONST]>;
+
+def ORYONWrite_1Cyc_2Uops_ST : SchedWriteRes<[ORYONST]> {
+ let NumMicroOps = 2;
+}
+
+def ORYONWrite_1Cyc_3Uops_ST : SchedWriteRes<[ORYONST]> {
+ let NumMicroOps = 3;
+}
+
+def ORYONWrite_1Cyc_4Uops_ST : SchedWriteRes<[ORYONST]> {
+ let NumMicroOps = 4;
+}
+
+def ORYONWrite_1Cyc_5Uops_ST : SchedWriteRes<[ORYONST]> {
+ let NumMicroOps = 5;
+}
+
+def ORYONWrite_1Cyc_6Uops_ST : SchedWriteRes<[ORYONST]> {
+ let NumMicroOps = 6;
+}
+
+def ORYONWrite_1Cyc_8Uops_ST : SchedWriteRes<[ORYONST]> {
+ let NumMicroOps = 8;
+}
+
+def ORYONWrite_1Cyc_10Uops_ST : SchedWriteRes<[ORYONST]> {
+ let NumMicroOps = 10;
+}
+
+// 1 cycle for neon write: float + ASIMD with Post/Pre Inc/Dec access
+// also includes Pair store until further informed
+def ORYONWrite_1Cyc_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 3;
+}
+
+def ORYONWrite_1Cyc_2Uops_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 2;
+}
+
+def ORYONWrite_1Cyc_3Uops_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 3;
+}
+
+def ORYONWrite_1Cyc_4Uops_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 4;
+}
+
+def ORYONWrite_1Cyc_5Uops_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 5;
+}
+
+def ORYONWrite_1Cyc_6Uops_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 6;
+}
+
+def ORYONWrite_1Cyc_8Uops_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 8;
+}
+
+def ORYONWrite_1Cyc_10Uops_ST_I012345 : SchedWriteRes<[ORYONST, ORYONI012345]> {
+ let NumMicroOps = 10;
+}
+
+// VXU resource definition
+
+// I2V instruction has 1 uOp
+// I2v with convert has 2 uOps
+// all I2V, V2I's throughputs are 2
+// On VXU doc, p37 -- latencies and throughput
+// P41, resource taken, P42, uOps
+def ORYONWrite_I2V_4Cyc_I45 : SchedWriteRes<[ORYONI2V]> {
+ let Latency = 4;
+}
+
+// inline a FCVT, so add one more uOp
+def ORYONWrite_I2V_7Cyc_I45 : SchedWriteRes<[ORYONI2V]> {
+ let Latency = 7;
+ let NumMicroOps = 2;
+}
+
+// V2I move instruction has 1/2 uOps, P42 in VXU doc
+// Latency is 3, FCVT is also 3 cycle
+// move + convert is 6 (3+3) cycles
+// throughput is 2
+def ORYONWrite_V2I_3Cyc_FP01 : SchedWriteRes<[ORYONV2I]> {
+ let Latency = 3;
+}
+
+// inline a FCVT, so add one more uOp
+def ORYONWrite_V2I_6Cyc_FP01 : SchedWriteRes<[ORYONV2I]> {
+ let Latency = 6;
+ let NumMicroOps = 2;
+}
+
+def ORYONWrite_V2V_2Cyc_FP0123 : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 2;
+}
+
+def ORYONWrite_V2V_3Cyc_FP0123 : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 3;
+}
+
+def ORYONWrite_V2V_6Cyc_FP01 : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 6;
+ let NumMicroOps = 3;
+}
+
+def ORYONWrite_4Cyc_FP0123 : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 4;
+}
+
+def ORYONWrite_3Cyc_FP0 : SchedWriteRes<[ORYONFP0]> {
+ let Latency = 3;
+}
+
+def ORYONWrite_3Cyc_FP0123 : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 3;
+}
+
+def ORYONWrite_3Cyc_2Uops_FP0123 : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 3;
+ let NumMicroOps = 2;
+}
+
+def ORYONWrite_2Cyc_FP0123 : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 2;
+}
+
+def ORYONWrite_2Cyc_FP01 : SchedWriteRes<[ORYONFP01]> {
+ let Latency = 2;
+}
+
+// 2 cycle on FP1
+def ORYONWrite_2Cyc_FP1 : SchedWriteRes<[ORYONFP1]> {
+ let Latency = 2;
+}
+
+// 3 cycle on FP1
+def ORYONWrite_3Cyc_FP1 : SchedWriteRes<[ORYONFP1]> {
+ let Latency = 3;
+}
+
+// 4 cycle , 0.5 throughput on FP1
+def ORYONWrite_4Cyc_FP1_RC4 : SchedWriteRes<[ORYONFP1]> {
+ let Latency = 4;
+ let ReleaseAtCycles = [4];
+}
+
+// 5 cycle , 1 throughput on FP1
+def ORYONWrite_5Cyc_FP1 : SchedWriteRes<[ORYONFP1]> {
+ let Latency = 5;
+}
+
+// 8 cycle , 2 throughput on FP0123
+def ORYONWrite_8Cyc_FP0123_RC : SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 8;
+ let ReleaseAtCycles = [2];
+}
+
+def ORYONWrite_6Cyc_FP3 : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 6;
+}
+
+def ORYONWrite_7Cyc_FP3 : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 7;
+}
+
+def ORYONWrite_8Cyc_FP3 : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 8;
+}
+
+def ORYONWrite_9Cyc_FP3 : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 9;
+}
+
+def ORYONWrite_10Cyc_FP3 : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 10;
+}
+
+def ORYONWrite_8Cyc_FP3_RC : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 8;
+ let ReleaseAtCycles = [2];
+}
+
+def ORYONWrite_10Cyc_FP3_RC : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 10;
+ let ReleaseAtCycles = [2];
+}
+
+def ORYONWrite_13Cyc_FP3_RC : SchedWriteRes<[ORYONFP3]> {
+ let Latency = 13;
+ let ReleaseAtCycles = [2];
+}
+
+def ORYONWrite_4Cyc_FP0123_RC :
+SchedWriteRes<[ORYONFP0123]> {
+ let Latency = 4;
+ let ReleaseAtCycles = [2];
+}
+
+def ORYONWrite_4Cyc_FP0123_FP0123_RC :
+SchedWriteRes<[ORYONFP0123, ORYONFP0123]> {
+ let Latency = 4;
+ let NumMicroOps = 2;
+ let ReleaseAtCycles = [2,2];
+}
+
+def ORYONWrite_4Cyc_FP0123_FP0123_FP0123_RC :
+SchedWriteRes<[ORYONFP0123, ORYONFP0123, ORYONFP0123]> {
+ let Latency = 4;
+ let NumMicroOps = 3;
+ let ReleaseAtCycles = [3,3,3];
+}
+
+def ORYONWrite_6Cyc_FP0123_FP0123_FP0123_FP0123_RC :
+SchedWriteRes<[ORYONFP0123, ORYONFP0123, ORYONFP0123, ORYONFP0123]> {
+ let Latency = 6;
+ let NumMicroOps = 4;
+ let ReleaseAtCycles = [6,6,6,6];
+}
+
+//===----------------------------------------------------------------------===//
+// Instruction Tables in IXU
+//===----------------------------------------------------------------------===//
+
+//---
+// Arithmetic Instructions
+//---
+
+//1, 1, 6
+def : InstRW<[ORYONWrite_1Cyc_I012345],
+ (instregex "^ADD(W|X)r(i|r|x)", "^SUB(W|X)r(i|r|x)")>;
----------------
efriedma-quic wrote:
Please verify that the modeling for ADDXrx etc. is correct. (This is the issue we discussed internally; leaving a note here so we don't forget.)
https://github.com/llvm/llvm-project/pull/91022
More information about the llvm-commits
mailing list