[llvm] [RISCV] Add a generic OOO CPU (PR #120712)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Dec 31 02:11:26 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Pengcheng Wang (wangpc-pp)
<details>
<summary>Changes</summary>
---
Patch is 104.22 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/120712.diff
6 Files Affected:
- (modified) llvm/lib/Target/RISCV/RISCV.td (+1-1)
- (modified) llvm/lib/Target/RISCV/RISCVProcessors.td (+2)
- (added) llvm/lib/Target/RISCV/RISCVSchedGenericOOO.td (+494)
- (added) llvm/test/tools/llvm-mca/RISCV/GenericOOO/atomic.s (+601)
- (added) llvm/test/tools/llvm-mca/RISCV/GenericOOO/floating-point.s (+483)
- (added) llvm/test/tools/llvm-mca/RISCV/GenericOOO/integer.s (+510)
``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCV.td b/llvm/lib/Target/RISCV/RISCV.td
index 963124140cd035..57843b9b93abd8 100644
--- a/llvm/lib/Target/RISCV/RISCV.td
+++ b/llvm/lib/Target/RISCV/RISCV.td
@@ -45,7 +45,7 @@ include "RISCVMacroFusion.td"
//===----------------------------------------------------------------------===//
// RISC-V Scheduling Models
//===----------------------------------------------------------------------===//
-
+include "RISCVSchedGenericOOO.td"
include "RISCVSchedMIPSP8700.td"
include "RISCVSchedRocket.td"
include "RISCVSchedSiFive7.td"
diff --git a/llvm/lib/Target/RISCV/RISCVProcessors.td b/llvm/lib/Target/RISCV/RISCVProcessors.td
index 61c7c21367036f..c846c27989d8c2 100644
--- a/llvm/lib/Target/RISCV/RISCVProcessors.td
+++ b/llvm/lib/Target/RISCV/RISCVProcessors.td
@@ -103,6 +103,8 @@ def GENERIC_RV64 : RISCVProcessorModel<"generic-rv64",
// Support generic for compatibility with other targets. The triple will be used
// to change to the appropriate rv32/rv64 version.
def GENERIC : RISCVTuneProcessorModel<"generic", NoSchedModel>, GenericTuneInfo;
+def GENERIC_OOO : RISCVTuneProcessorModel<"generic-ooo", GenericOOOModel>,
+ GenericTuneInfo;
def MIPS_P8700 : RISCVProcessorModel<"mips-p8700",
MIPSP8700Model,
diff --git a/llvm/lib/Target/RISCV/RISCVSchedGenericOOO.td b/llvm/lib/Target/RISCV/RISCVSchedGenericOOO.td
new file mode 100644
index 00000000000000..f7bf824ccebe0c
--- /dev/null
+++ b/llvm/lib/Target/RISCV/RISCVSchedGenericOOO.td
@@ -0,0 +1,494 @@
+//===-- RISCVSchedGenericOOO.td - Generic O3 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
+//
+//===----------------------------------------------------------------------===//
+
+//===----------------------------------------------------------------------===//
+// We assume that:
+// * 6-issue out-of-order CPU with 192 ROB entries.
+// * Units:
+// * IXU (Integer GenericOOOALU Unit): 4 units, only one can execute division.
+// * FXU (Floating-point Unit): 2 units.
+// * LSU (Load/Store Unit): 2 units.
+// * VXU (Vector Unit): 1 unit.
+// * Latency:
+// * Integer instructions: 1 cycle.
+// * Multiplication instructions: 4 cycles.
+// * Multiplication/Division instructions: 7-13 cycles.
+// * Floating-point instructions: 4-6 cycles.
+// * Vector instructions: 2-6 cycles.
+// * Load/Store:
+// * IXU: 4 cycles.
+// * FXU: 6 cycles.
+// * VXU: 6 cycles.
+// * Integer/floating-point/vector div/rem/sqrt/... are non-pipelined.
+//===----------------------------------------------------------------------===//
+
+def GenericOOOModel : SchedMachineModel {
+ int IssueWidth = 6;
+ int MicroOpBufferSize = 192;
+ int LoadLatency = 4;
+ int MispredictPenalty = 8;
+ let CompleteModel = 0;
+}
+
+let SchedModel = GenericOOOModel in {
+//===----------------------------------------------------------------------===//
+// Resource groups
+//===----------------------------------------------------------------------===//
+def GenericOOODIV : ProcResource<1>;
+def GenericOOOIXU : ProcResource<3>;
+def GenericOOOALU : ProcResGroup<[GenericOOODIV, GenericOOOIXU]>;
+def GenericOOOLSU : ProcResource<2>;
+def GenericOOOFPU : ProcResource<2>;
+// TODO: Add vector scheduling.
+// def GenericOOOVXU : ProcResource<1>;
+
+//===----------------------------------------------------------------------===//
+// Branches
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteJmp, [GenericOOOALU]>;
+def : WriteRes<WriteJalr, [GenericOOOALU]>;
+def : WriteRes<WriteJal, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Integer arithmetic and logic
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteIALU, [GenericOOOALU]>;
+def : WriteRes<WriteIALU32, [GenericOOOALU]>;
+def : WriteRes<WriteShiftImm, [GenericOOOALU]>;
+def : WriteRes<WriteShiftImm32, [GenericOOOALU]>;
+def : WriteRes<WriteShiftReg, [GenericOOOALU]>;
+def : WriteRes<WriteShiftReg32, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Integer multiplication
+//===----------------------------------------------------------------------===//
+let Latency = 4 in {
+ def : WriteRes<WriteIMul, [GenericOOOALU]>;
+ def : WriteRes<WriteIMul32, [GenericOOOALU]>;
+}
+
+//===----------------------------------------------------------------------===//
+// Integer division
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteIDiv32, [GenericOOODIV]> {
+ let Latency = 13;
+ let ReleaseAtCycles = [13];
+}
+def : WriteRes<WriteIDiv, [GenericOOODIV]> {
+ let Latency = 21;
+ let ReleaseAtCycles = [21];
+}
+def : WriteRes<WriteIRem32, [GenericOOODIV]> {
+ let Latency = 13;
+ let ReleaseAtCycles = [13];
+}
+def : WriteRes<WriteIRem, [GenericOOODIV]> {
+ let Latency = 21;
+ let ReleaseAtCycles = [21];
+}
+
+//===----------------------------------------------------------------------===//
+// Integer memory
+//===----------------------------------------------------------------------===//
+// Load
+let Latency = 4 in {
+ def : WriteRes<WriteLDB, [GenericOOOLSU]>;
+ def : WriteRes<WriteLDH, [GenericOOOLSU]>;
+ def : WriteRes<WriteLDW, [GenericOOOLSU]>;
+ def : WriteRes<WriteLDD, [GenericOOOLSU]>;
+}
+
+// Store
+def : WriteRes<WriteSTB, [GenericOOOLSU]>;
+def : WriteRes<WriteSTH, [GenericOOOLSU]>;
+def : WriteRes<WriteSTW, [GenericOOOLSU]>;
+def : WriteRes<WriteSTD, [GenericOOOLSU]>;
+
+//===----------------------------------------------------------------------===//
+// Atomic
+//===----------------------------------------------------------------------===//
+let Latency = 4 in {
+ def : WriteRes<WriteAtomicLDW, [GenericOOOLSU]>;
+ def : WriteRes<WriteAtomicLDD, [GenericOOOLSU]>;
+}
+
+let Latency = 5 in {
+ def : WriteRes<WriteAtomicW, [GenericOOOLSU]>;
+ def : WriteRes<WriteAtomicD, [GenericOOOLSU]>;
+}
+
+def : WriteRes<WriteAtomicSTW, [GenericOOOLSU]>;
+def : WriteRes<WriteAtomicSTD, [GenericOOOLSU]>;
+
+//===----------------------------------------------------------------------===//
+// Floating-point
+//===----------------------------------------------------------------------===//
+// Floating-point load
+let Latency = 6 in {
+ def : WriteRes<WriteFLD32, [GenericOOOLSU]>;
+ def : WriteRes<WriteFLD64, [GenericOOOLSU]>;
+}
+
+// Floating-point store
+def : WriteRes<WriteFST32, [GenericOOOLSU]>;
+def : WriteRes<WriteFST64, [GenericOOOLSU]>;
+
+// Arithmetic and logic
+let Latency = 4 in {
+ def : WriteRes<WriteFAdd32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFAdd64, [GenericOOOFPU]>;
+}
+
+let Latency = 5 in {
+ def : WriteRes<WriteFMul32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFMul64, [GenericOOOFPU]>;
+}
+
+let Latency = 6 in {
+ def : WriteRes<WriteFMA32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFMA64, [GenericOOOFPU]>;
+}
+
+def : WriteRes<WriteFSGNJ32, [GenericOOOFPU]>;
+def : WriteRes<WriteFSGNJ64, [GenericOOOFPU]>;
+def : WriteRes<WriteFMinMax32, [GenericOOOFPU]>;
+def : WriteRes<WriteFMinMax64, [GenericOOOFPU]>;
+
+// Compare
+let Latency = 2 in {
+ def : WriteRes<WriteFCmp32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCmp64, [GenericOOOFPU]>;
+}
+
+// Division
+let Latency = 13, ReleaseAtCycles = [13] in {
+ def : WriteRes<WriteFDiv32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFSqrt32, [GenericOOOFPU]>;
+}
+
+let Latency = 17, ReleaseAtCycles = [17] in {
+ def : WriteRes<WriteFDiv64, [GenericOOOFPU]>;
+ def : WriteRes<WriteFSqrt64, [GenericOOOFPU]>;
+}
+
+// Conversions
+let Latency = 4 in {
+ def : WriteRes<WriteFCvtI32ToF32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtI32ToF64, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtI64ToF32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtI64ToF64, [GenericOOOFPU]>;
+}
+
+let Latency = 4 in {
+ def : WriteRes<WriteFCvtF32ToI32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtF32ToI64, [GenericOOOFPU]>;
+}
+
+let Latency = 4 in {
+ def : WriteRes<WriteFCvtF64ToI32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtF64ToI64, [GenericOOOFPU]>;
+}
+
+let Latency = 4 in {
+ def : WriteRes<WriteFCvtF64ToF32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtF32ToF64, [GenericOOOFPU]>;
+}
+
+let Latency = 6 in {
+ def : WriteRes<WriteFMovI32ToF32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFMovI64ToF64, [GenericOOOFPU]>;
+ def : WriteRes<WriteFMovF32ToI32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFMovF64ToI64, [GenericOOOFPU]>;
+}
+
+// Classify
+def : WriteRes<WriteFClass32, [GenericOOOFPU]>;
+def : WriteRes<WriteFClass64, [GenericOOOFPU]>;
+
+//===----------------------------------------------------------------------===//
+// Zicsr extension
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteCSR, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Zabha extension
+//===----------------------------------------------------------------------===//
+let Latency = 5 in {
+ def : WriteRes<WriteAtomicB, [GenericOOOLSU]>;
+ def : WriteRes<WriteAtomicH, [GenericOOOLSU]>;
+}
+
+//===----------------------------------------------------------------------===//
+// Zba extension
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteSHXADD, [GenericOOOALU]>;
+def : WriteRes<WriteSHXADD32, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Zbb extension
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteCLZ, [GenericOOOALU]>;
+def : WriteRes<WriteCTZ, [GenericOOOALU]>;
+def : WriteRes<WriteCPOP, [GenericOOOALU]>;
+def : WriteRes<WriteCLZ32, [GenericOOOALU]>;
+def : WriteRes<WriteCTZ32, [GenericOOOALU]>;
+def : WriteRes<WriteCPOP32, [GenericOOOALU]>;
+def : WriteRes<WriteRotateReg, [GenericOOOALU]>;
+def : WriteRes<WriteRotateImm, [GenericOOOALU]>;
+def : WriteRes<WriteRotateReg32, [GenericOOOALU]>;
+def : WriteRes<WriteRotateImm32, [GenericOOOALU]>;
+def : WriteRes<WriteREV8, [GenericOOOALU]>;
+def : WriteRes<WriteORCB, [GenericOOOALU]>;
+def : WriteRes<WriteIMinMax, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Zbc extension
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteCLMUL, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Zbs extension
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteSingleBit, [GenericOOOALU]>;
+def : WriteRes<WriteSingleBitImm, [GenericOOOALU]>;
+def : WriteRes<WriteBEXT, [GenericOOOALU]>;
+def : WriteRes<WriteBEXTI, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Zbkb extension
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteBREV8, [GenericOOOALU]>;
+def : WriteRes<WritePACK, [GenericOOOALU]>;
+def : WriteRes<WritePACK32, [GenericOOOALU]>;
+def : WriteRes<WriteZIP, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Zbkx extension
+//===----------------------------------------------------------------------===//
+def : WriteRes<WriteXPERM, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Zfa extension
+//===----------------------------------------------------------------------===//
+let Latency = 3 in {
+ def : WriteRes<WriteFRoundF16, [GenericOOOFPU]>;
+ def : WriteRes<WriteFRoundF32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFRoundF64, [GenericOOOFPU]>;
+}
+
+let Latency = 5 in {
+ def : WriteRes<WriteFLI16, [GenericOOOFPU]>;
+ def : WriteRes<WriteFLI32, [GenericOOOFPU]>;
+ def : WriteRes<WriteFLI64, [GenericOOOFPU]>;
+}
+
+//===----------------------------------------------------------------------===//
+// Zfh extension
+//===----------------------------------------------------------------------===//
+// Zfhmin
+// Load/Store
+let Latency = 6 in
+def : WriteRes<WriteFLD16, [GenericOOOLSU]>;
+def : WriteRes<WriteFST16, [GenericOOOLSU]>;
+
+// Conversions
+let Latency = 3 in {
+ def : WriteRes<WriteFCvtF16ToF64, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtF64ToF16, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtF32ToF16, [GenericOOOFPU]>;
+ def : WriteRes<WriteFCvtF16ToF32, [GenericOOOFPU]>;
+}
+
+let Latency = 4 in {
+ def : WriteRes<WriteFMovI16ToF16, [GenericOOOFPU]>;
+ def : WriteRes<WriteFMovF16ToI16, [GenericOOOFPU]>;
+}
+
+// Other than Zfhmin
+let Latency = 4 in {
+ def : WriteRes<WriteFCvtI64ToF16, []>;
+ def : WriteRes<WriteFCvtI32ToF16, []>;
+ def : WriteRes<WriteFCvtF16ToI64, []>;
+ def : WriteRes<WriteFCvtF16ToI32, []>;
+}
+
+// Arithmetic and logic
+let Latency = 4 in
+def : WriteRes<WriteFAdd16, [GenericOOOFPU]>;
+
+let Latency = 5 in
+def : WriteRes<WriteFMul16, [GenericOOOFPU]>;
+
+let Latency = 6 in
+def : WriteRes<WriteFMA16, [GenericOOOFPU]>;
+
+def : WriteRes<WriteFSGNJ16, [GenericOOOFPU]>;
+def : WriteRes<WriteFMinMax16, [GenericOOOFPU]>;
+
+// Compare
+let Latency = 2 in
+def : WriteRes<WriteFCmp16, [GenericOOOFPU]>;
+
+// Division
+let Latency = 9, ReleaseAtCycles = [9] in {
+ def : WriteRes<WriteFDiv16, [GenericOOOFPU]>;
+ def : WriteRes<WriteFSqrt16, [GenericOOOFPU]>;
+}
+
+// Classify
+def : WriteRes<WriteFClass16, [GenericOOOFPU]>;
+
+//===----------------------------------------------------------------------===//
+// Misc
+//===----------------------------------------------------------------------===//
+let Latency = 0 in
+def : WriteRes<WriteNop, [GenericOOOALU]>;
+
+//===----------------------------------------------------------------------===//
+// Bypass and advance
+//===----------------------------------------------------------------------===//
+def : ReadAdvance<ReadJmp, 0>;
+def : ReadAdvance<ReadJalr, 0>;
+def : ReadAdvance<ReadCSR, 0>;
+def : ReadAdvance<ReadStoreData, 0>;
+def : ReadAdvance<ReadMemBase, 0>;
+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<ReadIDiv, 0>;
+def : ReadAdvance<ReadIDiv32, 0>;
+def : ReadAdvance<ReadIRem, 0>;
+def : ReadAdvance<ReadIRem32, 0>;
+def : ReadAdvance<ReadIMul, 0>;
+def : ReadAdvance<ReadIMul32, 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<ReadFMemBase, 0>;
+def : ReadAdvance<ReadFAdd32, 0>;
+def : ReadAdvance<ReadFAdd64, 0>;
+def : ReadAdvance<ReadFMul32, 0>;
+def : ReadAdvance<ReadFMA32, 0>;
+def : ReadAdvance<ReadFMA32Addend, 0>;
+def : ReadAdvance<ReadFMul64, 0>;
+def : ReadAdvance<ReadFMA64, 0>;
+def : ReadAdvance<ReadFMA64Addend, 0>;
+def : ReadAdvance<ReadFDiv32, 0>;
+def : ReadAdvance<ReadFDiv64, 0>;
+def : ReadAdvance<ReadFSqrt32, 0>;
+def : ReadAdvance<ReadFSqrt64, 0>;
+def : ReadAdvance<ReadFCmp32, 0>;
+def : ReadAdvance<ReadFCmp64, 0>;
+def : ReadAdvance<ReadFSGNJ32, 0>;
+def : ReadAdvance<ReadFSGNJ64, 0>;
+def : ReadAdvance<ReadFMinMax32, 0>;
+def : ReadAdvance<ReadFMinMax64, 0>;
+def : ReadAdvance<ReadFCvtF32ToI32, 0>;
+def : ReadAdvance<ReadFCvtF32ToI64, 0>;
+def : ReadAdvance<ReadFCvtF64ToI32, 0>;
+def : ReadAdvance<ReadFCvtF64ToI64, 0>;
+def : ReadAdvance<ReadFCvtI32ToF32, 0>;
+def : ReadAdvance<ReadFCvtI32ToF64, 0>;
+def : ReadAdvance<ReadFCvtI64ToF32, 0>;
+def : ReadAdvance<ReadFCvtI64ToF64, 0>;
+def : ReadAdvance<ReadFCvtF32ToF64, 0>;
+def : ReadAdvance<ReadFCvtF64ToF32, 0>;
+def : ReadAdvance<ReadFMovF32ToI32, 0>;
+def : ReadAdvance<ReadFMovI32ToF32, 0>;
+def : ReadAdvance<ReadFMovF64ToI64, 0>;
+def : ReadAdvance<ReadFMovI64ToF64, 0>;
+def : ReadAdvance<ReadFClass32, 0>;
+def : ReadAdvance<ReadFClass64, 0>;
+
+// Zabha
+def : ReadAdvance<ReadAtomicBA, 0>;
+def : ReadAdvance<ReadAtomicBD, 0>;
+def : ReadAdvance<ReadAtomicHA, 0>;
+def : ReadAdvance<ReadAtomicHD, 0>;
+
+// Zba extension
+def : ReadAdvance<ReadSHXADD, 0>;
+def : ReadAdvance<ReadSHXADD32, 0>;
+
+// Zbb extension
+def : ReadAdvance<ReadRotateImm, 0>;
+def : ReadAdvance<ReadRotateImm32, 0>;
+def : ReadAdvance<ReadRotateReg, 0>;
+def : ReadAdvance<ReadRotateReg32, 0>;
+def : ReadAdvance<ReadCLZ, 0>;
+def : ReadAdvance<ReadCLZ32, 0>;
+def : ReadAdvance<ReadCTZ, 0>;
+def : ReadAdvance<ReadCTZ32, 0>;
+def : ReadAdvance<ReadCPOP, 0>;
+def : ReadAdvance<ReadCPOP32, 0>;
+def : ReadAdvance<ReadREV8, 0>;
+def : ReadAdvance<ReadORCB, 0>;
+def : ReadAdvance<ReadIMinMax, 0>;
+
+// Zbc extension
+def : ReadAdvance<ReadCLMUL, 0>;
+
+// Zbs extension
+def : ReadAdvance<ReadSingleBit, 0>;
+def : ReadAdvance<ReadSingleBitImm, 0>;
+
+// Zbkb
+def : ReadAdvance<ReadBREV8, 0>;
+def : ReadAdvance<ReadPACK, 0>;
+def : ReadAdvance<ReadPACK32, 0>;
+def : ReadAdvance<ReadZIP, 0>;
+
+// Zbkx
+def : ReadAdvance<ReadXPERM, 0>;
+
+// Zfa extension
+def : ReadAdvance<ReadFRoundF32, 0>;
+def : ReadAdvance<ReadFRoundF64, 0>;
+def : ReadAdvance<ReadFRoundF16, 0>;
+
+// Zfh extension
+def : ReadAdvance<ReadFCvtF16ToF64, 0>;
+def : ReadAdvance<ReadFCvtF64ToF16, 0>;
+def : ReadAdvance<ReadFCvtF32ToF16, 0>;
+def : ReadAdvance<ReadFCvtF16ToF32, 0>;
+def : ReadAdvance<ReadFMovI16ToF16, 0>;
+def : ReadAdvance<ReadFMovF16ToI16, 0>;
+
+def : ReadAdvance<ReadFAdd16, 0>;
+def : ReadAdvance<ReadFClass16, 0>;
+def : ReadAdvance<ReadFCvtI64ToF16, 0>;
+def : ReadAdvance<ReadFCvtI32ToF16, 0>;
+def : ReadAdvance<ReadFCvtF16ToI64, 0>;
+def : ReadAdvance<ReadFCvtF16ToI32, 0>;
+def : ReadAdvance<ReadFDiv16, 0>;
+def : ReadAdvance<ReadFCmp16, 0>;
+def : ReadAdvance<ReadFMA16, 0>;
+def : ReadAdvance<ReadFMA16Addend, 0>;
+def : ReadAdvance<ReadFMinMax16, 0>;
+def : ReadAdvance<ReadFMul16, 0>;
+def : ReadAdvance<ReadFSGNJ16, 0>;
+def : ReadAdvance<ReadFSqrt16, 0>;
+
+//===----------------------------------------------------------------------===//
+// Unsupported extensions
+//===----------------------------------------------------------------------===//
+defm : UnsupportedSchedV;
+defm : UnsupportedSchedZvk;
+defm : UnsupportedSchedZvkned;
+defm : UnsupportedSchedSFB;
+defm : UnsupportedSchedXsfvcp;
+}
diff --git a/llvm/test/tools/llvm-mca/RISCV/GenericOOO/atomic.s b/llvm/test/tools/llvm-mca/RISCV/GenericOOO/atomic.s
new file mode 100644
index 00000000000000..e8c19eaa4c618d
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/RISCV/GenericOOO/atomic.s
@@ -0,0 +1,601 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=riscv64 -mattr=+rva23u64,+zabha -mcpu=generic-ooo --all-stats -iterations=1 < %s | FileCheck %s
+
+# Zalrsc
+lr.w t0, (t1)
+lr.w.aq t1, (t2)
+lr.w.rl t2, (t3)
+lr.w.aqrl t3, (t4)
+sc.w t6, t5, (t4)
+sc.w.aq t5, t4, (t3)
+sc.w.rl t4, t3, (t2)
+sc.w.aqrl t3, t2, (t1)
+
+lr.d t0, (t1)
+lr.d.aq t1, (t2)
+lr.d.rl t2, (t3)
+lr.d.aqrl t3, (t4)
+sc.d t6, t5, (t4)
+sc.d.aq t5, t4, (t3)
+sc.d.rl t4, t3, (t2)
+sc.d.aqrl t3, t2, (t1)
+
+# Zaamo
+amoswap.w a4, ra, (s0)
+amoadd.w a1, a2, (a3)
+amoxor.w a2, a3, (a4)
+amoand.w a3, a4, (a5)
+amoor.w a4, a5, (a6)
+amomin.w a5, a6, (a7)
+amomax.w s7, s6, (s5)
+amominu.w s6, s5, (s4)
+amomaxu.w s5, s4, (s3)
+
+amoswap.w.aq a4, ra, (s0)
+amoadd.w.aq a1, a2, (a3)
+amoxor.w.aq a2, a3, (a4)
+amoand.w.aq a3, a4, (a5)
+amoor.w.aq a4, a5, (a6)
+amomin.w.aq a5, a6, (a7)
+amomax.w.aq s7, s6, (s5)
+amominu.w.aq s6, s5, (s4)
+amomaxu.w.aq s5, s4, (s3)
+
+amoswap.w.rl a4, ra, (s0)
+amoadd.w.rl a1, a2, (a3)
+amoxor.w.rl a2, a3, (a4)
+amoand.w.rl a3, a4, (a5)
+amoor.w.rl a4, a5, (a6)
+amomin.w.rl a5, a6, (a7)
+amomax.w.rl s7, s6, (s5)
+amominu.w.rl s6, s5, (s4)
+amomaxu.w.rl s5, s4, (s3)
+
+amoswap.w.aqrl a4, ra, (s0)
+amoadd.w.aqrl a1, a2, (a3)
+amoxor.w.aqrl a2, a3, (a4)
+amoand.w.aqrl a3, a4, (a5)
+amoor.w.aqrl ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/120712
More information about the llvm-commits
mailing list