mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 02:33:06 +01:00
10839866a1
This patch implements initial backend support for a -mtune CPU controlled by a "tune-cpu" function attribute. If the attribute is not present X86 will use the resolved CPU from target-cpu attribute or command line. This patch adds MC layer support a tune CPU. Each CPU now has two sets of features stored in their GenSubtargetInfo.inc tables . These features lists are passed separately to the Processor and ProcessorModel classes in tablegen. The tune list defaults to an empty list to avoid changes to non-X86. This annoyingly increases the size of static tables on all target as we now store 24 more bytes per CPU. I haven't quantified the overall impact, but I can if we're concerned. One new test is added to X86 to show a few tuning features with mismatched tune-cpu and target-cpu/target-feature attributes to demonstrate independent control. Another new test is added to demonstrate that the scheduler model follows the tune CPU. I have not added a -mtune to llc/opt or MC layer command line yet. With no attributes we'll just use the -mcpu for both. MC layer tools will always follow the normal CPU for tuning. Differential Revision: https://reviews.llvm.org/D85165
68 lines
2.2 KiB
C++
68 lines
2.2 KiB
C++
//===- NVPTXSubtarget.cpp - NVPTX Subtarget Information -------------------===//
|
|
//
|
|
// 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 implements the NVPTX specific subclass of TargetSubtarget.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "NVPTXSubtarget.h"
|
|
#include "NVPTXTargetMachine.h"
|
|
|
|
using namespace llvm;
|
|
|
|
#define DEBUG_TYPE "nvptx-subtarget"
|
|
|
|
#define GET_SUBTARGETINFO_ENUM
|
|
#define GET_SUBTARGETINFO_TARGET_DESC
|
|
#define GET_SUBTARGETINFO_CTOR
|
|
#include "NVPTXGenSubtargetInfo.inc"
|
|
|
|
static cl::opt<bool>
|
|
NoF16Math("nvptx-no-f16-math", cl::ZeroOrMore, cl::Hidden,
|
|
cl::desc("NVPTX Specific: Disable generation of f16 math ops."),
|
|
cl::init(false));
|
|
|
|
// Pin the vtable to this file.
|
|
void NVPTXSubtarget::anchor() {}
|
|
|
|
NVPTXSubtarget &NVPTXSubtarget::initializeSubtargetDependencies(StringRef CPU,
|
|
StringRef FS) {
|
|
// Provide the default CPU if we don't have one.
|
|
TargetName = std::string(CPU.empty() ? "sm_20" : CPU);
|
|
|
|
ParseSubtargetFeatures(TargetName, /*TuneCPU*/ TargetName, FS);
|
|
|
|
// Set default to PTX 3.2 (CUDA 5.5)
|
|
if (PTXVersion == 0) {
|
|
PTXVersion = 32;
|
|
}
|
|
|
|
return *this;
|
|
}
|
|
|
|
NVPTXSubtarget::NVPTXSubtarget(const Triple &TT, const std::string &CPU,
|
|
const std::string &FS,
|
|
const NVPTXTargetMachine &TM)
|
|
: NVPTXGenSubtargetInfo(TT, CPU, /*TuneCPU*/ CPU, FS), PTXVersion(0),
|
|
SmVersion(20), TM(TM), InstrInfo(),
|
|
TLInfo(TM, initializeSubtargetDependencies(CPU, FS)), FrameLowering() {}
|
|
|
|
bool NVPTXSubtarget::hasImageHandles() const {
|
|
// Enable handles for Kepler+, where CUDA supports indirect surfaces and
|
|
// textures
|
|
if (TM.getDrvInterface() == NVPTX::CUDA)
|
|
return (SmVersion >= 30);
|
|
|
|
// Disabled, otherwise
|
|
return false;
|
|
}
|
|
|
|
bool NVPTXSubtarget::allowFP16Math() const {
|
|
return hasFP16Math() && NoF16Math == false;
|
|
}
|