summaryrefslogtreecommitdiffstats
path: root/contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
diff options
context:
space:
mode:
authordim <dim@FreeBSD.org>2015-05-27 20:26:41 +0000
committerdim <dim@FreeBSD.org>2015-05-27 20:26:41 +0000
commit5ef8fd3549d38e883a31881636be3dc2a275de20 (patch)
treebd13a22d9db57ccf3eddbc07b32c18109521d050 /contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
parent77794ebe2d5718eb502c93ec32f8ccae4d8a0b7b (diff)
parent782067d0278612ee75d024b9b135c221c327e9e8 (diff)
downloadFreeBSD-src-5ef8fd3549d38e883a31881636be3dc2a275de20.zip
FreeBSD-src-5ef8fd3549d38e883a31881636be3dc2a275de20.tar.gz
Merge llvm trunk r238337 from ^/vendor/llvm/dist, resolve conflicts, and
preserve our customizations, where necessary.
Diffstat (limited to 'contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp')
-rw-r--r--contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp64
1 files changed, 39 insertions, 25 deletions
diff --git a/contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp b/contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
index c7f9507..ac27c30 100644
--- a/contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
+++ b/contrib/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -17,6 +17,7 @@
#include "NVPTXAllocaHoisting.h"
#include "NVPTXLowerAggrCopies.h"
#include "NVPTXTargetObjectFile.h"
+#include "NVPTXTargetTransformInfo.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/MachineFunctionAnalysis.h"
@@ -24,12 +25,12 @@
#include "llvm/CodeGen/Passes.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/IRPrintingPasses.h"
+#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Verifier.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCInstrInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSubtargetInfo.h"
-#include "llvm/PassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/FormattedStream.h"
@@ -49,6 +50,7 @@ using namespace llvm;
namespace llvm {
void initializeNVVMReflectPass(PassRegistry&);
void initializeGenericToNVVMPass(PassRegistry&);
+void initializeNVPTXAllocaHoistingPass(PassRegistry &);
void initializeNVPTXAssignValidGlobalNamesPass(PassRegistry&);
void initializeNVPTXFavorNonGenericAddrSpacesPass(PassRegistry &);
void initializeNVPTXLowerStructArgsPass(PassRegistry &);
@@ -63,20 +65,37 @@ extern "C" void LLVMInitializeNVPTXTarget() {
// but it's very NVPTX-specific.
initializeNVVMReflectPass(*PassRegistry::getPassRegistry());
initializeGenericToNVVMPass(*PassRegistry::getPassRegistry());
+ initializeNVPTXAllocaHoistingPass(*PassRegistry::getPassRegistry());
initializeNVPTXAssignValidGlobalNamesPass(*PassRegistry::getPassRegistry());
initializeNVPTXFavorNonGenericAddrSpacesPass(
*PassRegistry::getPassRegistry());
initializeNVPTXLowerStructArgsPass(*PassRegistry::getPassRegistry());
}
+static std::string computeDataLayout(bool is64Bit) {
+ std::string Ret = "e";
+
+ if (!is64Bit)
+ Ret += "-p:32:32";
+
+ Ret += "-i64:64-v16:16-v32:32-n16:32:64";
+
+ return Ret;
+}
+
NVPTXTargetMachine::NVPTXTargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL, bool is64bit)
- : LLVMTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL),
- TLOF(make_unique<NVPTXTargetObjectFile>()),
- Subtarget(TT, CPU, FS, *this, is64bit) {
+ : LLVMTargetMachine(T, computeDataLayout(is64bit), TT, CPU, FS, Options, RM,
+ CM, OL),
+ is64bit(is64bit), TLOF(make_unique<NVPTXTargetObjectFile>()),
+ Subtarget(TT, CPU, FS, *this) {
+ if (Triple(TT).getOS() == Triple::NVCL)
+ drvInterface = NVPTX::NVCL;
+ else
+ drvInterface = NVPTX::CUDA;
initAsmInfo();
}
@@ -124,12 +143,9 @@ TargetPassConfig *NVPTXTargetMachine::createPassConfig(PassManagerBase &PM) {
return PassConfig;
}
-void NVPTXTargetMachine::addAnalysisPasses(PassManagerBase &PM) {
- // Add first the target-independent BasicTTI pass, then our NVPTX pass. This
- // allows the NVPTX pass to delegate to the target independent layer when
- // appropriate.
- PM.add(createBasicTargetTransformInfoPass(this));
- PM.add(createNVPTXTargetTransformInfoPass(this));
+TargetIRAnalysis NVPTXTargetMachine::getTargetIRAnalysis() {
+ return TargetIRAnalysis(
+ [this](Function &) { return TargetTransformInfo(NVPTXTTIImpl(this)); });
}
void NVPTXPassConfig::addIRPasses() {
@@ -148,29 +164,27 @@ void NVPTXPassConfig::addIRPasses() {
addPass(createNVPTXAssignValidGlobalNamesPass());
addPass(createGenericToNVVMPass());
addPass(createNVPTXFavorNonGenericAddrSpacesPass());
+ // FavorNonGenericAddrSpaces shortcuts unnecessary addrspacecasts, and leave
+ // them unused. We could remove dead code in an ad-hoc manner, but that
+ // requires manual work and might be error-prone.
+ addPass(createDeadCodeEliminationPass());
addPass(createSeparateConstOffsetFromGEPPass());
- // The SeparateConstOffsetFromGEP pass creates variadic bases that can be used
- // by multiple GEPs. Run GVN or EarlyCSE to really reuse them. GVN generates
- // significantly better code than EarlyCSE for some of our benchmarks.
+ // ReassociateGEPs exposes more opportunites for SLSR. See
+ // the example in reassociate-geps-and-slsr.ll.
+ addPass(createStraightLineStrengthReducePass());
+ // SeparateConstOffsetFromGEP and SLSR creates common expressions which GVN or
+ // EarlyCSE can reuse. GVN generates significantly better code than EarlyCSE
+ // for some of our benchmarks.
if (getOptLevel() == CodeGenOpt::Aggressive)
addPass(createGVNPass());
else
addPass(createEarlyCSEPass());
- // Both FavorNonGenericAddrSpaces and SeparateConstOffsetFromGEP may leave
- // some dead code. We could remove dead code in an ad-hoc manner, but that
- // requires manual work and might be error-prone.
- //
- // The FavorNonGenericAddrSpaces pass shortcuts unnecessary addrspacecasts,
- // and leave them unused.
- //
- // SeparateConstOffsetFromGEP rebuilds a new index from the old index, and the
- // old index and some of its intermediate results may become unused.
- addPass(createDeadCodeEliminationPass());
+ // Run NaryReassociate after EarlyCSE/GVN to be more effective.
+ addPass(createNaryReassociatePass());
}
bool NVPTXPassConfig::addInstSelector() {
- const NVPTXSubtarget &ST =
- getTM<NVPTXTargetMachine>().getSubtarget<NVPTXSubtarget>();
+ const NVPTXSubtarget &ST = *getTM<NVPTXTargetMachine>().getSubtargetImpl();
addPass(createLowerAggrCopies());
addPass(createAllocaHoisting());
OpenPOWER on IntegriCloud