[llvm] Reland "[RISCV] Add scheduling model for mips p8700 CPU" (PR #120550)

Djordje Todorovic via llvm-commits llvm-commits at lists.llvm.org
Thu Dec 19 02:38:10 PST 2024


https://github.com/djtodoro created https://github.com/llvm/llvm-project/pull/120550

Add `UnsupportedSchedZfhmin`.

>From ae33ba17d32e476c5066ab14d5151d134fdc0457 Mon Sep 17 00:00:00 2001
From: Djordje Todorovic <djordje.todorovic at htecgroup.com>
Date: Thu, 19 Dec 2024 10:09:45 +0100
Subject: [PATCH] Reland "[RISCV] Add scheduling model for mips p8700 CPU"

Add UnsupportedSchedZfhmin.
---
 llvm/lib/Target/RISCV/RISCV.td               |   1 +
 llvm/lib/Target/RISCV/RISCVProcessors.td     |   3 +-
 llvm/lib/Target/RISCV/RISCVSchedMIPSP8700.td | 281 +++++++++++++++++++
 llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s  | 143 ++++++++++
 4 files changed, 426 insertions(+), 2 deletions(-)
 create mode 100644 llvm/lib/Target/RISCV/RISCVSchedMIPSP8700.td
 create mode 100644 llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s

diff --git a/llvm/lib/Target/RISCV/RISCV.td b/llvm/lib/Target/RISCV/RISCV.td
index 00c3d702e12a22..1df6f9ae1944c8 100644
--- a/llvm/lib/Target/RISCV/RISCV.td
+++ b/llvm/lib/Target/RISCV/RISCV.td
@@ -46,6 +46,7 @@ include "RISCVMacroFusion.td"
 // RISC-V Scheduling Models
 //===----------------------------------------------------------------------===//
 
+include "RISCVSchedMIPSP8700.td"
 include "RISCVSchedRocket.td"
 include "RISCVSchedSiFive7.td"
 include "RISCVSchedSiFiveP400.td"
diff --git a/llvm/lib/Target/RISCV/RISCVProcessors.td b/llvm/lib/Target/RISCV/RISCVProcessors.td
index 445e084d07686b..053a3b11f39bc5 100644
--- a/llvm/lib/Target/RISCV/RISCVProcessors.td
+++ b/llvm/lib/Target/RISCV/RISCVProcessors.td
@@ -105,7 +105,7 @@ def GENERIC_RV64 : RISCVProcessorModel<"generic-rv64",
 def GENERIC : RISCVTuneProcessorModel<"generic", NoSchedModel>, GenericTuneInfo;
 
 def MIPS_P8700 : RISCVProcessorModel<"mips-p8700",
-                                     NoSchedModel,
+                                     MIPSP8700Model,
                                      [Feature64Bit,
                                       FeatureStdExtI,
                                       FeatureStdExtM,
@@ -321,7 +321,6 @@ def SIFIVE_P470 : RISCVProcessorModel<"sifive-p470", SiFiveP400Model,
                                                   [TuneNoSinkSplatOperands,
                                                    TuneVXRMPipelineFlush])>;
 
-
 def SIFIVE_P670 : RISCVProcessorModel<"sifive-p670", SiFiveP600Model,
                                       !listconcat(RVA22U64Features,
                                       [FeatureStdExtV,
diff --git a/llvm/lib/Target/RISCV/RISCVSchedMIPSP8700.td b/llvm/lib/Target/RISCV/RISCVSchedMIPSP8700.td
new file mode 100644
index 00000000000000..550f83a59b8b0e
--- /dev/null
+++ b/llvm/lib/Target/RISCV/RISCVSchedMIPSP8700.td
@@ -0,0 +1,281 @@
+//===-- RISCVSchedMIPSP8700.td - MIPS RISC-V Processor -----*- 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
+//
+//===----------------------------------------------------------------------===//
+
+//===----------------------------------------------------------------------===//
+// P8700 - a RISC-V processor by MIPS.
+// Pipelines:
+//   - 2 Integer Arithmetic and Logical Units (ALU and AL2)
+//   - Multiply / Divide Unit (MDU)
+//   - Branch Unit (CTI)
+//   - Load Store Unit (LSU)
+//   - Short Floating Point Pipe (FPUS)
+//   - Long Floating Point Pipe (FPUL)
+//===----------------------------------------------------------------------===//
+
+def MIPSP8700Model : SchedMachineModel {
+  int IssueWidth = 4;
+  int MicroOpBufferSize = 96;
+  int LoadLatency = 4;
+  int MispredictPenalty = 8;
+  let CompleteModel = 0;
+}
+
+let SchedModel = MIPSP8700Model in {
+// Handle ALQ Pipelines.
+// It contains 1 ALU Unit only.
+def p8700ALQ : ProcResource<1> { let BufferSize = 16; }
+
+// Handle AGQ Pipelines.
+def p8700AGQ : ProcResource<3> { let BufferSize = 16; }
+def p8700IssueAL2 : ProcResource<1> { let Super = p8700AGQ; }
+def p8700IssueCTI : ProcResource<1> { let Super = p8700AGQ; }
+def p8700IssueLSU : ProcResource<1> { let Super = p8700AGQ; }
+def p8700WriteEitherALU : ProcResGroup<[p8700ALQ, p8700IssueAL2]>;
+
+// Handle Multiply Divide Pipe.
+def p8700GpDiv : ProcResource<1>;
+def p8700GpMul : ProcResource<1>;
+
+def : WriteRes<WriteIALU, [p8700WriteEitherALU]>;
+def : WriteRes<WriteIALU32, [p8700WriteEitherALU]>;
+def : WriteRes<WriteShiftImm, [p8700WriteEitherALU]>;
+def : WriteRes<WriteShiftImm32, [p8700WriteEitherALU]>;
+def : WriteRes<WriteShiftReg, [p8700WriteEitherALU]>;
+def : WriteRes<WriteShiftReg32, [p8700WriteEitherALU]>;
+
+// Handle zba.
+def : WriteRes<WriteSHXADD, [p8700WriteEitherALU]>;
+def : WriteRes<WriteSHXADD32, [p8700WriteEitherALU]>;
+
+// Handle zbb.
+let Latency = 2 in {
+def : WriteRes<WriteCLZ, [p8700IssueAL2]>;
+def : WriteRes<WriteCTZ, [p8700IssueAL2]>;
+def : WriteRes<WriteCPOP, [p8700IssueAL2]>;
+def : WriteRes<WriteCLZ32, [p8700IssueAL2]>;
+def : WriteRes<WriteCTZ32, [p8700IssueAL2]>;
+def : WriteRes<WriteCPOP32, [p8700IssueAL2]>;
+}
+def : WriteRes<WriteRotateReg, [p8700WriteEitherALU]>;
+def : WriteRes<WriteRotateImm, [p8700WriteEitherALU]>;
+def : WriteRes<WriteRotateReg32, [p8700WriteEitherALU]>;
+def : WriteRes<WriteRotateImm32, [p8700WriteEitherALU]>;
+def : WriteRes<WriteREV8, [p8700WriteEitherALU]>;
+def : WriteRes<WriteORCB, [p8700WriteEitherALU]>;
+def : WriteRes<WriteIMinMax, [p8700WriteEitherALU]>;
+
+let Latency = 0 in
+def : WriteRes<WriteNop, [p8700WriteEitherALU]>;
+
+let Latency = 4 in {
+def : WriteRes<WriteLDB, [p8700IssueLSU]>;
+def : WriteRes<WriteLDH, [p8700IssueLSU]>;
+def : WriteRes<WriteLDW, [p8700IssueLSU]>;
+def : WriteRes<WriteLDD, [p8700IssueLSU]>;
+
+def : WriteRes<WriteAtomicW, [p8700IssueLSU]>;
+def : WriteRes<WriteAtomicD, [p8700IssueLSU]>;
+def : WriteRes<WriteAtomicLDW, [p8700IssueLSU]>;
+def : WriteRes<WriteAtomicLDD, [p8700IssueLSU]>;
+}
+
+let Latency = 8 in {
+def : WriteRes<WriteFLD32, [p8700IssueLSU]>;
+def : WriteRes<WriteFLD64, [p8700IssueLSU]>;
+}
+
+let Latency = 3 in {
+def : WriteRes<WriteSTB, [p8700IssueLSU]>;
+def : WriteRes<WriteSTH, [p8700IssueLSU]>;
+def : WriteRes<WriteSTW, [p8700IssueLSU]>;
+def : WriteRes<WriteSTD, [p8700IssueLSU]>;
+
+def : WriteRes<WriteAtomicSTW, [p8700IssueLSU]>;
+def : WriteRes<WriteAtomicSTD, [p8700IssueLSU]>;
+}
+
+def : WriteRes<WriteFST32, [p8700IssueLSU]>;
+def : WriteRes<WriteFST64, [p8700IssueLSU]>;
+
+let Latency = 7 in {
+def : WriteRes<WriteFMovI32ToF32, [p8700IssueLSU]>;
+def : WriteRes<WriteFMovF32ToI32, [p8700IssueLSU]>;
+def : WriteRes<WriteFMovI64ToF64, [p8700IssueLSU]>;
+def : WriteRes<WriteFMovF64ToI64, [p8700IssueLSU]>;
+}
+
+let Latency = 4 in {
+def : WriteRes<WriteIMul, [p8700GpMul]>;
+def : WriteRes<WriteIMul32, [p8700GpMul]>;
+}
+
+let Latency = 7, ReleaseAtCycles = [7] in {
+def : WriteRes<WriteIDiv, [p8700GpDiv]>;
+def : WriteRes<WriteIDiv32,  [p8700GpDiv]>;
+def : WriteRes<WriteIRem, [p8700GpDiv]>;
+def : WriteRes<WriteIRem32, [p8700GpDiv]>;
+}
+
+def : WriteRes<WriteCSR, [p8700ALQ]>;
+
+// Handle CTI Pipeline.
+def : WriteRes<WriteJmp, [p8700IssueCTI]>;
+def : WriteRes<WriteJalr, [p8700IssueCTI]>;
+let Latency = 2 in {
+def : WriteRes<WriteJal, [p8700IssueCTI]>;
+def : WriteRes<WriteJalr, [p8700IssueCTI]>;
+}
+
+// Handle FPU Pipelines.
+def p8700FPQ : ProcResource<3> { let BufferSize = 16; }
+def p8700IssueFPUS : ProcResource<1> { let Super = p8700FPQ; }
+def p8700IssueFPUL : ProcResource<1> { let Super = p8700FPQ; }
+def p8700FpuApu    : ProcResource<1>;
+def p8700FpuLong   : ProcResource<1>;
+
+let Latency = 4 in {
+def : WriteRes<WriteFCvtI32ToF32, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtI32ToF64, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtI64ToF32, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtI64ToF64, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtF32ToI32, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtF32ToI64, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtF32ToF64, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtF64ToI32, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtF64ToI64, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFCvtF64ToF32, [p8700IssueFPUL, p8700FpuApu]>;
+
+def : WriteRes<WriteFAdd32, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFAdd64, [p8700IssueFPUL, p8700FpuApu]>;
+}
+
+let Latency = 2 in {
+def : WriteRes<WriteFSGNJ32, [p8700IssueFPUS, p8700FpuApu]>;
+def : WriteRes<WriteFMinMax32, [p8700IssueFPUS, p8700FpuApu]>;
+def : WriteRes<WriteFSGNJ64, [p8700IssueFPUS, p8700FpuApu]>;
+def : WriteRes<WriteFMinMax64, [p8700IssueFPUS, p8700FpuApu]>;
+
+def : WriteRes<WriteFCmp32, [p8700IssueFPUS, p8700FpuApu]>;
+def : WriteRes<WriteFCmp64, [p8700IssueFPUS, p8700FpuApu]>;
+}
+
+def : WriteRes<WriteFClass32, [p8700IssueFPUS, p8700FpuApu]>;
+def : WriteRes<WriteFClass64, [p8700IssueFPUS, p8700FpuApu]>;
+
+let Latency = 8 in {
+def : WriteRes<WriteFMA32, [p8700FpuLong, p8700FpuApu]>;
+def : WriteRes<WriteFMA64, [p8700FpuLong, p8700FpuApu]>;
+}
+
+let Latency = 5 in {
+def : WriteRes<WriteFMul32, [p8700FpuLong, p8700FpuApu]>;
+def : WriteRes<WriteFMul64, [p8700FpuLong, p8700FpuApu]>;
+}
+
+let Latency = 11, ReleaseAtCycles = [1, 11] in {
+def : WriteRes<WriteFDiv32, [p8700FpuLong, p8700FpuApu]>;
+def : WriteRes<WriteFSqrt32, [p8700FpuLong, p8700FpuApu]>;
+}
+
+let Latency = 17, ReleaseAtCycles = [1, 17] in {
+def : WriteRes<WriteFDiv64, [p8700IssueFPUL, p8700FpuApu]>;
+def : WriteRes<WriteFSqrt64, [p8700IssueFPUL, p8700FpuApu]>;
+}
+
+// Bypass and advance.
+def : ReadAdvance<ReadIALU, 0>;
+def : ReadAdvance<ReadIALU32, 0>;
+def : ReadAdvance<ReadShiftImm, 0>;
+def : ReadAdvance<ReadShiftImm32, 0>;
+def : ReadAdvance<ReadShiftReg, 0>;
+def : ReadAdvance<ReadShiftReg32, 0>;
+def : ReadAdvance<ReadSHXADD, 0>;
+def : ReadAdvance<ReadSHXADD32, 0>;
+def : ReadAdvance<ReadRotateReg, 0>;
+def : ReadAdvance<ReadRotateImm, 0>;
+def : ReadAdvance<ReadCLZ, 0>;
+def : ReadAdvance<ReadCTZ, 0>;
+def : ReadAdvance<ReadCPOP, 0>;
+def : ReadAdvance<ReadRotateReg32, 0>;
+def : ReadAdvance<ReadRotateImm32, 0>;
+def : ReadAdvance<ReadCLZ32, 0>;
+def : ReadAdvance<ReadCTZ32, 0>;
+def : ReadAdvance<ReadCPOP32, 0>;
+def : ReadAdvance<ReadREV8, 0>;
+def : ReadAdvance<ReadORCB, 0>;
+def : ReadAdvance<ReadIMul, 0>;
+def : ReadAdvance<ReadIMul32, 0>;
+def : ReadAdvance<ReadIDiv, 0>;
+def : ReadAdvance<ReadIDiv32, 0>;
+def : ReadAdvance<ReadJmp, 0>;
+def : ReadAdvance<ReadJalr, 0>;
+def : ReadAdvance<ReadFMovI32ToF32, 0>;
+def : ReadAdvance<ReadFMovF32ToI32, 0>;
+def : ReadAdvance<ReadFMovI64ToF64, 0>;
+def : ReadAdvance<ReadFMovF64ToI64, 0>;
+def : ReadAdvance<ReadFSGNJ32, 0>;
+def : ReadAdvance<ReadFMinMax32, 0>;
+def : ReadAdvance<ReadFSGNJ64, 0>;
+def : ReadAdvance<ReadFMinMax64, 0>;
+def : ReadAdvance<ReadFCmp32, 0>;
+def : ReadAdvance<ReadFCmp64, 0>;
+def : ReadAdvance<ReadFCvtI32ToF32, 0>;
+def : ReadAdvance<ReadFCvtI32ToF64, 0>;
+def : ReadAdvance<ReadFCvtI64ToF32, 0>;
+def : ReadAdvance<ReadFCvtI64ToF64, 0>;
+def : ReadAdvance<ReadFCvtF32ToI32, 0>;
+def : ReadAdvance<ReadFCvtF32ToI64, 0>;
+def : ReadAdvance<ReadFCvtF32ToF64, 0>;
+def : ReadAdvance<ReadFCvtF64ToI32, 0>;
+def : ReadAdvance<ReadFCvtF64ToI64, 0>;
+def : ReadAdvance<ReadFCvtF64ToF32, 0>;
+def : ReadAdvance<ReadFAdd32, 0>;
+def : ReadAdvance<ReadFAdd64, 0>;
+def : ReadAdvance<ReadFMul32, 0>;
+def : ReadAdvance<ReadFMul64, 0>;
+def : ReadAdvance<ReadFMA32, 0>;
+def : ReadAdvance<ReadFMA32Addend, 0>;
+def : ReadAdvance<ReadFMA64, 0>;
+def : ReadAdvance<ReadFMA64Addend, 0>;
+def : ReadAdvance<ReadFDiv32, 0>;
+def : ReadAdvance<ReadFSqrt32, 0>;
+def : ReadAdvance<ReadFDiv64, 0>;
+def : ReadAdvance<ReadFSqrt64, 0>;
+def : ReadAdvance<ReadAtomicWA, 0>;
+def : ReadAdvance<ReadAtomicWD, 0>;
+def : ReadAdvance<ReadAtomicDA, 0>;
+def : ReadAdvance<ReadAtomicDD, 0>;
+def : ReadAdvance<ReadAtomicLDW, 0>;
+def : ReadAdvance<ReadAtomicLDD, 0>;
+def : ReadAdvance<ReadAtomicSTW, 0>;
+def : ReadAdvance<ReadAtomicSTD, 0>;
+def : ReadAdvance<ReadFStoreData, 0>;
+def : ReadAdvance<ReadCSR, 0>;
+def : ReadAdvance<ReadMemBase, 0>;
+def : ReadAdvance<ReadStoreData, 0>;
+def : ReadAdvance<ReadFMemBase, 0>;
+def : ReadAdvance<ReadFClass32, 0>;
+def : ReadAdvance<ReadFClass64, 0>;
+def : ReadAdvance<ReadIMinMax, 0>;
+def : ReadAdvance<ReadIRem, 0>;
+def : ReadAdvance<ReadIRem32, 0>;
+
+// Unsupported extensions.
+defm : UnsupportedSchedV;
+defm : UnsupportedSchedZbc;
+defm : UnsupportedSchedZbs;
+defm : UnsupportedSchedZbkb;
+defm : UnsupportedSchedZbkx;
+defm : UnsupportedSchedZfa;
+defm : UnsupportedSchedZfhmin;
+defm : UnsupportedSchedSFB;
+defm : UnsupportedSchedZabha;
+defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedZvk;
+defm : UnsupportedSchedZvkned;
+}
diff --git a/llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s b/llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s
new file mode 100644
index 00000000000000..ca91f6bb970d8b
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s
@@ -0,0 +1,143 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=riscv64 -mcpu=mips-p8700 -timeline -iterations=1 < %s | FileCheck %s
+
+# A few instructions to test the pipeline:
+# - Integer division (IDiv) exercises the p8700GpDiv resource.
+# - Integer multiplication (IMul) uses p8700GpMul.
+# - Floating-point multiplication uses the FPUL pipeline.
+# - Load/Store instructions use the LSU pipeline.
+# - Simple ALU instructions test the p8700WriteEitherALU and p8700IssueAL2 resources.
+# - A jump instruction to test the CTI pipeline.
+
+  .text
+  .globl _start
+_start:
+
+# Integer division: a0 = a1 / a2
+# Exercises p8700GpDiv resource.
+  div     a0, a1, a2
+
+# Integer multiplication: a4 = a1 * a2
+# Exercises p8700GpMul resource.
+  mul     a4, a1, a2
+
+# Floating-point multiply: f1 = f2 * f3 (single precision)
+# Exercises p8700FpuLong + p8700FpuApu resources.
+  fmul.s  f1, f2, f3
+
+# Load/Store: load word from a0 into a3, then store a3 into a1
+# Exercises p8700IssueLSU resource.
+  lw      a3, 0(a0)
+  sw      a3, 0(a1)
+
+# Simple ALU operations (adding two registers, rotating bits)
+# Exercises p8700WriteEitherALU.
+  add     a5, a1, a2
+  ror     a6, a5, a2
+
+# A jump instruction: a simple forward jump
+# Exercises p8700IssueCTI resource.
+  jal     x0, .Lend
+
+  add     a7, a4, a0  # Instruction after jump (won't execute)
+.Lend:
+  nop
+
+# CHECK:      Iterations:        1
+# CHECK-NEXT: Instructions:      10
+# CHECK-NEXT: Total Cycles:      17
+# CHECK-NEXT: Total uOps:        10
+
+# CHECK:      Dispatch Width:    4
+# CHECK-NEXT: uOps Per Cycle:    0.59
+# CHECK-NEXT: IPC:               0.59
+# CHECK-NEXT: Block RThroughput: 7.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      7     7.00                        div	a0, a1, a2
+# CHECK-NEXT:  1      4     1.00                        mul	a4, a1, a2
+# CHECK-NEXT:  1      5     1.00                        fmul.s	ft1, ft2, ft3
+# CHECK-NEXT:  1      4     1.00    *                   lw	a3, 0(a0)
+# CHECK-NEXT:  1      3     1.00           *            sw	a3, 0(a1)
+# CHECK-NEXT:  1      1     0.50                        add	a5, a1, a2
+# CHECK-NEXT:  1      1     0.50                        ror	a6, a5, a2
+# CHECK-NEXT:  1      1     1.00                        j	.Lend
+# CHECK-NEXT:  1      1     0.50                        add	a7, a4, a0
+# CHECK-NEXT:  1      0     0.50                        nop
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0.0] - p8700AGQ
+# CHECK-NEXT: [0.1] - p8700AGQ
+# CHECK-NEXT: [0.2] - p8700AGQ
+# CHECK-NEXT: [1]   - p8700ALQ
+# CHECK-NEXT: [2.0] - p8700FPQ
+# CHECK-NEXT: [2.1] - p8700FPQ
+# CHECK-NEXT: [2.2] - p8700FPQ
+# CHECK-NEXT: [3]   - p8700FpuApu
+# CHECK-NEXT: [4]   - p8700FpuLong
+# CHECK-NEXT: [5]   - p8700GpDiv
+# CHECK-NEXT: [6]   - p8700GpMul
+# CHECK-NEXT: [7]   - p8700IssueAL2
+# CHECK-NEXT: [8]   - p8700IssueCTI
+# CHECK-NEXT: [9]   - p8700IssueFPUL
+# CHECK-NEXT: [10]  - p8700IssueFPUS
+# CHECK-NEXT: [11]  - p8700IssueLSU
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0.0]  [0.1]  [0.2]  [1]    [2.0]  [2.1]  [2.2]  [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]
+# CHECK-NEXT: 1.00   1.00   1.00   2.00    -      -      -     1.00   1.00   7.00   1.00   2.00   1.00    -      -     2.00
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0.0]  [0.1]  [0.2]  [1]    [2.0]  [2.1]  [2.2]  [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -     7.00    -      -      -      -      -      -     div	a0, a1, a2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -     mul	a4, a1, a2
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00    -      -      -      -      -      -      -     fmul.s	ft1, ft2, ft3
+# CHECK-NEXT:  -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   lw	a3, 0(a0)
+# CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   sw	a3, 0(a1)
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     add	a5, a1, a2
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -     ror	a6, a5, a2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -      -      -      -     1.00    -      -      -     j	.Lend
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -     add	a7, a4, a0
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     nop
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0123456
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeER.    ..   div	a0, a1, a2
+# CHECK-NEXT: [0,1]     DeeeeE---R.    ..   mul	a4, a1, a2
+# CHECK-NEXT: [0,2]     DeeeeeE--R.    ..   fmul.s	ft1, ft2, ft3
+# CHECK-NEXT: [0,3]     D=======eeeeER ..   lw	a3, 0(a0)
+# CHECK-NEXT: [0,4]     .D==========eeeER   sw	a3, 0(a1)
+# CHECK-NEXT: [0,5]     .DeE------------R   add	a5, a1, a2
+# CHECK-NEXT: [0,6]     .D=eE-----------R   ror	a6, a5, a2
+# CHECK-NEXT: [0,7]     .DeE------------R   j	.Lend
+# CHECK-NEXT: [0,8]     . D=====eE------R   add	a7, a4, a0
+# CHECK-NEXT: [0,9]     . DE------------R   nop
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     1     1.0    1.0    0.0       div	a0, a1, a2
+# CHECK-NEXT: 1.     1     1.0    1.0    3.0       mul	a4, a1, a2
+# CHECK-NEXT: 2.     1     1.0    1.0    2.0       fmul.s	ft1, ft2, ft3
+# CHECK-NEXT: 3.     1     8.0    0.0    0.0       lw	a3, 0(a0)
+# CHECK-NEXT: 4.     1     11.0   0.0    0.0       sw	a3, 0(a1)
+# CHECK-NEXT: 5.     1     1.0    1.0    12.0      add	a5, a1, a2
+# CHECK-NEXT: 6.     1     2.0    0.0    11.0      ror	a6, a5, a2
+# CHECK-NEXT: 7.     1     1.0    1.0    12.0      j	.Lend
+# CHECK-NEXT: 8.     1     6.0    0.0    6.0       add	a7, a4, a0
+# CHECK-NEXT: 9.     1     1.0    1.0    12.0      nop
+# CHECK-NEXT:        1     3.3    0.6    5.8       <total>



More information about the llvm-commits mailing list