[NVPTX] Allow libcalls that are defined in the current module.

The patch adds a possibility to make library calls on NVPTX.

An important thing about library functions - they must be defined within
the current module. This basically should guarantee that we produce a
valid PTX assembly (without calls to not defined functions). The one who
wants to use the libcalls is probably will have to link against
compiler-rt or any other implementation.

Currently, it's completely impossible to make library calls because of
error LLVM ERROR: Cannot select: i32 = ExternalSymbol '...'. But we can
lower ExternalSymbol to TargetExternalSymbol and verify if the function
definition is available.

Also, there was an issue with a DAG during legalisation. When we expand
instruction into libcall, the inner call-chain isn't being "integrated"
into outer chain. Since the last "data-flow" (call retval load) node is
located in call-chain earlier than CALLSEQ_END node, the latter becomes
a leaf and therefore a dead node (and is being removed quite fast).
Proposed here solution relies on another data-flow pseudo nodes
(ProxyReg) which purpose is only to keep CALLSEQ_END at legalisation and
instruction selection phases - we remove the pseudo instructions before
register scheduling phase.

Patch by Denys Zariaiev!

Differential Revision: https://reviews.llvm.org/D34708

llvm-svn: 350069
This commit is contained in:
Justin Lebar 2018-12-26 19:12:31 +00:00
parent 423b65333d
commit 49fac56ea3
17 changed files with 508 additions and 16 deletions

View File

@ -1128,6 +1128,13 @@ public:
/// Expand the specified \c ISD::VACOPY node as the Legalize pass would.
SDValue expandVACopy(SDNode *Node);
/// Returs an GlobalAddress of the function from the current module with
/// name matching the given ExternalSymbol. Additionally can provide the
/// matched function.
/// Panics the function doesn't exists.
SDValue getSymbolFunctionGlobalAddress(SDValue Op,
Function **TargetFunction = nullptr);
/// *Mutate* the specified node in-place to have the
/// specified operands. If the resultant node already exists in the DAG,
/// this does not modify the specified node, instead it returns the node that

View File

@ -8464,6 +8464,32 @@ SDValue SelectionDAG::makeEquivalentMemoryOrdering(LoadSDNode *OldLoad,
return TokenFactor;
}
SDValue SelectionDAG::getSymbolFunctionGlobalAddress(SDValue Op,
Function **OutFunction) {
assert(isa<ExternalSymbolSDNode>(Op) && "Node should be an ExternalSymbol");
auto *Symbol = cast<ExternalSymbolSDNode>(Op)->getSymbol();
auto *Module = MF->getFunction().getParent();
auto *Function = Module->getFunction(Symbol);
if (OutFunction != nullptr)
*OutFunction = Function;
if (Function != nullptr) {
auto PtrTy = TLI->getPointerTy(getDataLayout(), Function->getAddressSpace());
return getGlobalAddress(Function, SDLoc(Op), PtrTy);
}
std::string ErrorStr;
raw_string_ostream ErrorFormatter(ErrorStr);
ErrorFormatter << "Undefined external symbol ";
ErrorFormatter << '"' << Symbol << '"';
ErrorFormatter.flush();
report_fatal_error(ErrorStr);
}
//===----------------------------------------------------------------------===//
// SDNode Class
//===----------------------------------------------------------------------===//

View File

@ -32,6 +32,7 @@ set(NVPTXCodeGen_sources
NVPTXUtilities.cpp
NVVMIntrRange.cpp
NVVMReflect.cpp
NVPTXProxyRegErasure.cpp
)
add_llvm_target(NVPTXCodeGen ${NVPTXCodeGen_sources})

View File

@ -53,6 +53,7 @@ FunctionPass *createNVPTXImageOptimizerPass();
FunctionPass *createNVPTXLowerArgsPass(const NVPTXTargetMachine *TM);
BasicBlockPass *createNVPTXLowerAllocaPass();
MachineFunctionPass *createNVPTXPeephole();
MachineFunctionPass *createNVPTXProxyRegErasurePass();
Target &getTheNVPTXTarget32();
Target &getTheNVPTXTarget64();

View File

@ -730,6 +730,11 @@ void NVPTXAsmPrinter::emitDeclarations(const Module &M, raw_ostream &O) {
for (Module::const_iterator FI = M.begin(), FE = M.end(); FI != FE; ++FI) {
const Function *F = &*FI;
if (F->getAttributes().hasFnAttribute("nvptx-libcall-callee")) {
emitDeclaration(F, O);
continue;
}
if (F->isDeclaration()) {
if (F->use_empty())
continue;

View File

@ -663,6 +663,8 @@ const char *NVPTXTargetLowering::getTargetNodeName(unsigned Opcode) const {
return "NVPTXISD::CallSeqEnd";
case NVPTXISD::CallPrototype:
return "NVPTXISD::CallPrototype";
case NVPTXISD::ProxyReg:
return "NVPTXISD::ProxyReg";
case NVPTXISD::LoadV2:
return "NVPTXISD::LoadV2";
case NVPTXISD::LoadV4:
@ -1666,6 +1668,18 @@ SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
// indirect calls but is always null for libcalls.
bool isIndirectCall = !Func && CS;
if (isa<ExternalSymbolSDNode>(Callee)) {
Function* CalleeFunc = nullptr;
// Try to find the callee in the current module.
Callee = DAG.getSymbolFunctionGlobalAddress(Callee, &CalleeFunc);
assert(CalleeFunc != nullptr && "Libcall callee must be set.");
// Set the "libcall callee" attribute to indicate that the function
// must always have a declaration.
CalleeFunc->addFnAttr("nvptx-libcall-callee", "true");
}
if (isIndirectCall) {
// This is indirect function call case : PTX requires a prototype of the
// form
@ -1738,6 +1752,9 @@ SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
InFlag = Chain.getValue(1);
}
SmallVector<SDValue, 16> ProxyRegOps;
SmallVector<Optional<MVT>, 16> ProxyRegTruncates;
// Generate loads from param memory/moves from registers for result
if (Ins.size() > 0) {
SmallVector<EVT, 16> VTs;
@ -1808,11 +1825,14 @@ SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
MachineMemOperand::MOLoad);
for (unsigned j = 0; j < NumElts; ++j) {
SDValue Ret = RetVal.getValue(j);
ProxyRegOps.push_back(RetVal.getValue(j));
if (needTruncate)
Ret = DAG.getNode(ISD::TRUNCATE, dl, Ins[VecIdx + j].VT, Ret);
InVals.push_back(Ret);
ProxyRegTruncates.push_back(Optional<MVT>(Ins[VecIdx + j].VT));
else
ProxyRegTruncates.push_back(Optional<MVT>());
}
Chain = RetVal.getValue(NumElts);
InFlag = RetVal.getValue(NumElts + 1);
@ -1828,8 +1848,29 @@ SDValue NVPTXTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
DAG.getIntPtrConstant(uniqueCallSite + 1, dl,
true),
InFlag, dl);
InFlag = Chain.getValue(1);
uniqueCallSite++;
// Append ProxyReg instructions to the chain to make sure that `callseq_end`
// will not get lost. Otherwise, during libcalls expansion, the nodes can become
// dangling.
for (unsigned i = 0; i < ProxyRegOps.size(); ++i) {
SDValue Ret = DAG.getNode(
NVPTXISD::ProxyReg, dl,
DAG.getVTList(ProxyRegOps[i].getSimpleValueType(), MVT::Other, MVT::Glue),
{ Chain, ProxyRegOps[i], InFlag }
);
Chain = Ret.getValue(1);
InFlag = Ret.getValue(2);
if (ProxyRegTruncates[i].hasValue()) {
Ret = DAG.getNode(ISD::TRUNCATE, dl, ProxyRegTruncates[i].getValue(), Ret);
}
InVals.push_back(Ret);
}
// set isTailCall to false for now, until we figure out how to express
// tail call optimization in PTX
isTailCall = false;

View File

@ -51,6 +51,7 @@ enum NodeType : unsigned {
CallSeqBegin,
CallSeqEnd,
CallPrototype,
ProxyReg,
FUN_SHFL_CLAMP,
FUN_SHFR_CLAMP,
MUL_WIDE_SIGNED,

View File

@ -1885,6 +1885,7 @@ def SDTStoreRetvalProfile : SDTypeProfile<0, 2, [SDTCisInt<0>]>;
def SDTStoreRetvalV2Profile : SDTypeProfile<0, 3, [SDTCisInt<0>]>;
def SDTStoreRetvalV4Profile : SDTypeProfile<0, 5, [SDTCisInt<0>]>;
def SDTPseudoUseParamProfile : SDTypeProfile<0, 1, []>;
def SDTProxyRegProfile : SDTypeProfile<1, 1, []>;
def DeclareParam :
SDNode<"NVPTXISD::DeclareParam", SDTDeclareParamProfile,
@ -1972,6 +1973,9 @@ def PseudoUseParam :
def RETURNNode :
SDNode<"NVPTXISD::RETURN", SDTCallArgMarkProfile,
[SDNPHasChain, SDNPSideEffect]>;
def ProxyReg :
SDNode<"NVPTXISD::ProxyReg", SDTProxyRegProfile,
[SDNPHasChain, SDNPOutGlue, SDNPInGlue, SDNPSideEffect]>;
let mayLoad = 1 in {
class LoadParamMemInst<NVPTXRegClass regclass, string opstr> :
@ -2249,6 +2253,21 @@ def PseudoUseParamI16 : PseudoUseParamInst<Int16Regs>;
def PseudoUseParamF64 : PseudoUseParamInst<Float64Regs>;
def PseudoUseParamF32 : PseudoUseParamInst<Float32Regs>;
class ProxyRegInst<string SzStr, NVPTXRegClass regclass> :
NVPTXInst<(outs regclass:$dst), (ins regclass:$src),
!strconcat("mov.", SzStr, " \t$dst, $src;"),
[(set regclass:$dst, (ProxyReg regclass:$src))]>;
let isCodeGenOnly=1, isPseudo=1 in {
def ProxyRegI1 : ProxyRegInst<"pred", Int1Regs>;
def ProxyRegI16 : ProxyRegInst<"b16", Int16Regs>;
def ProxyRegI32 : ProxyRegInst<"b32", Int32Regs>;
def ProxyRegI64 : ProxyRegInst<"b64", Int64Regs>;
def ProxyRegF16 : ProxyRegInst<"b16", Float16Regs>;
def ProxyRegF32 : ProxyRegInst<"f32", Float32Regs>;
def ProxyRegF64 : ProxyRegInst<"f64", Float64Regs>;
def ProxyRegF16x2 : ProxyRegInst<"b32", Float16x2Regs>;
}
//
// Load / Store Handling
@ -2541,7 +2560,7 @@ let mayStore=1, hasSideEffects=0 in {
class F_BITCONVERT<string SzStr, NVPTXRegClass regclassIn,
NVPTXRegClass regclassOut> :
NVPTXInst<(outs regclassOut:$d), (ins regclassIn:$a),
!strconcat("mov.b", !strconcat(SzStr, " \t$d, $a;")),
!strconcat("mov.b", SzStr, " \t$d, $a;"),
[(set regclassOut:$d, (bitconvert regclassIn:$a))]>;
def BITCONVERT_16_I2F : F_BITCONVERT<"16", Int16Regs, Float16Regs>;

View File

@ -0,0 +1,122 @@
//===- NVPTXProxyRegErasure.cpp - NVPTX Proxy Register Instruction Erasure -==//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// The pass is needed to remove ProxyReg instructions and restore related
// registers. The instructions were needed at instruction selection stage to
// make sure that callseq_end nodes won't be removed as "dead nodes". This can
// happen when we expand instructions into libcalls and the call site doesn't
// care about the libcall chain. Call site cares about data flow only, and the
// latest data flow node happens to be before callseq_end. Therefore the node
// becomes dangling and "dead". The ProxyReg acts like an additional data flow
// node *after* the callseq_end in the chain and ensures that everything will be
// preserved.
//
//===----------------------------------------------------------------------===//
#include "NVPTX.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
using namespace llvm;
namespace llvm {
void initializeNVPTXProxyRegErasurePass(PassRegistry &);
}
namespace {
struct NVPTXProxyRegErasure : public MachineFunctionPass {
public:
static char ID;
NVPTXProxyRegErasure() : MachineFunctionPass(ID) {
initializeNVPTXProxyRegErasurePass(*PassRegistry::getPassRegistry());
}
bool runOnMachineFunction(MachineFunction &MF) override;
StringRef getPassName() const override {
return "NVPTX Proxy Register Instruction Erasure";
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
MachineFunctionPass::getAnalysisUsage(AU);
}
private:
void replaceMachineInstructionUsage(MachineFunction &MF, MachineInstr &MI);
void replaceRegisterUsage(MachineInstr &Instr, MachineOperand &From,
MachineOperand &To);
};
} // namespace
char NVPTXProxyRegErasure::ID = 0;
INITIALIZE_PASS(NVPTXProxyRegErasure, "nvptx-proxyreg-erasure", "NVPTX ProxyReg Erasure", false, false)
bool NVPTXProxyRegErasure::runOnMachineFunction(MachineFunction &MF) {
SmallVector<MachineInstr *, 16> RemoveList;
for (auto &BB : MF) {
for (auto &MI : BB) {
switch (MI.getOpcode()) {
case NVPTX::ProxyRegI1:
case NVPTX::ProxyRegI16:
case NVPTX::ProxyRegI32:
case NVPTX::ProxyRegI64:
case NVPTX::ProxyRegF16:
case NVPTX::ProxyRegF16x2:
case NVPTX::ProxyRegF32:
case NVPTX::ProxyRegF64:
replaceMachineInstructionUsage(MF, MI);
RemoveList.push_back(&MI);
break;
}
}
}
for (auto *MI : RemoveList) {
MI->eraseFromParent();
}
return !RemoveList.empty();
}
void NVPTXProxyRegErasure::replaceMachineInstructionUsage(MachineFunction &MF,
MachineInstr &MI) {
auto &InOp = *MI.uses().begin();
auto &OutOp = *MI.defs().begin();
assert(InOp.isReg() && "ProxyReg input operand should be a register.");
assert(OutOp.isReg() && "ProxyReg output operand should be a register.");
for (auto &BB : MF) {
for (auto &I : BB) {
replaceRegisterUsage(I, OutOp, InOp);
}
}
}
void NVPTXProxyRegErasure::replaceRegisterUsage(MachineInstr &Instr,
MachineOperand &From,
MachineOperand &To) {
for (auto &Op : Instr.uses()) {
if (Op.isReg() && Op.getReg() == From.getReg()) {
Op.setReg(To.getReg());
}
}
}
MachineFunctionPass *llvm::createNVPTXProxyRegErasurePass() {
return new NVPTXProxyRegErasure();
}

View File

@ -68,6 +68,7 @@ void initializeNVPTXAssignValidGlobalNamesPass(PassRegistry&);
void initializeNVPTXLowerAggrCopiesPass(PassRegistry &);
void initializeNVPTXLowerArgsPass(PassRegistry &);
void initializeNVPTXLowerAllocaPass(PassRegistry &);
void initializeNVPTXProxyRegErasurePass(PassRegistry &);
} // end namespace llvm
@ -87,6 +88,7 @@ extern "C" void LLVMInitializeNVPTXTarget() {
initializeNVPTXLowerArgsPass(PR);
initializeNVPTXLowerAllocaPass(PR);
initializeNVPTXLowerAggrCopiesPass(PR);
initializeNVPTXProxyRegErasurePass(PR);
}
static std::string computeDataLayout(bool is64Bit, bool UseShortPointers) {
@ -160,6 +162,7 @@ public:
void addIRPasses() override;
bool addInstSelector() override;
void addPreRegAlloc() override;
void addPostRegAlloc() override;
void addMachineSSAOptimization() override;
@ -301,6 +304,11 @@ bool NVPTXPassConfig::addInstSelector() {
return false;
}
void NVPTXPassConfig::addPreRegAlloc() {
// Remove Proxy Register pseudo instructions used to keep `callseq_end` alive.
addPass(createNVPTXProxyRegErasurePass());
}
void NVPTXPassConfig::addPostRegAlloc() {
addPass(createNVPTXPrologEpilogPass(), false);
if (getOptLevel() != CodeGenOpt::None) {

View File

@ -0,0 +1,22 @@
; RUN: llc < %s -march=nvptx 2>&1 | FileCheck %s
; Make sure the example doesn't crash with segfault
; CHECK: .visible .func ({{.*}}) loop
define i32 @loop(i32, i32) {
entry:
br label %loop
loop:
%i = phi i32 [ %0, %entry ], [ %res, %loop ]
%res = call i32 @div(i32 %i, i32 %1)
%exitcond = icmp eq i32 %res, %0
br i1 %exitcond, label %exit, label %loop
exit:
ret i32 %res
}
define i32 @div(i32, i32) {
ret i32 0
}

View File

@ -0,0 +1,31 @@
; RUN: llc < %s -march=nvptx 2>&1 | FileCheck %s
; Allow to make libcalls that are defined in the current module
; Underlying libcall declaration
; CHECK: .visible .func (.param .align 16 .b8 func_retval0[16]) __umodti3
define i128 @remainder(i128, i128) {
bb0:
; CHECK: { // callseq 0, 0
; CHECK: call.uni (retval0),
; CHECK-NEXT: __umodti3,
; CHECK-NEXT: (
; CHECK-NEXT: param0,
; CHECK-NEXT: param1
; CHECK-NEXT: );
; CHECK-NEXT: ld.param.v2.b64 {%[[REG0:rd[0-9]+]], %[[REG1:rd[0-9]+]]}, [retval0+0];
; CHECK-NEXT: } // callseq 0
%a = urem i128 %0, %1
br label %bb1
bb1:
; CHECK-NEXT: st.param.v2.b64 [func_retval0+0], {%[[REG0]], %[[REG1]]};
; CHECK-NEXT: ret;
ret i128 %a
}
; Underlying libcall definition
; CHECK: .visible .func (.param .align 16 .b8 func_retval0[16]) __umodti3(
define i128 @__umodti3(i128, i128) {
ret i128 0
}

View File

@ -1,7 +1,7 @@
; RUN: not llc < %s -march=nvptx 2>&1 | FileCheck %s
; used to panic on failed assetion and now fails with a "Cannot select"
; used to panic on failed assertion and now fails with an "Undefined external symbol"
; CHECK: LLVM ERROR: Cannot select: {{t28|0x[0-9a-f]+}}: i32 = ExternalSymbol'__umodti3'
; CHECK: LLVM ERROR: Undefined external symbol "__umodti3"
define hidden i128 @remainder(i128, i128) {
%3 = urem i128 %0, %1
ret i128 %3

View File

@ -0,0 +1,10 @@
; RUN: not llc < %s -march=nvptx 2>&1 | FileCheck %s
; used to seqfault and now fails with an "Undefined external symbol"
; CHECK: LLVM ERROR: Undefined external symbol "__powidf2"
define double @powi(double, i32) {
%a = call double @llvm.powi.f64(double %0, i32 %1)
ret double %a
}
declare double @llvm.powi.f64(double, i32) nounwind readnone

View File

@ -0,0 +1,25 @@
; RUN: llc -march=nvptx64 -stop-before=nvptx-proxyreg-erasure < %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=MIR --check-prefix=MIR-BEFORE
; RUN: llc -march=nvptx64 -stop-after=nvptx-proxyreg-erasure < %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=MIR --check-prefix=MIR-AFTER
; Check ProxyRegErasure pass MIR manipulation.
declare <4 x i32> @callee_vec_i32()
define <4 x i32> @check_vec_i32() {
; MIR: body:
; MIR-DAG: Callseq_Start {{[0-9]+}}, {{[0-9]+}}
; MIR-DAG: %0:int32regs, %1:int32regs, %2:int32regs, %3:int32regs = LoadParamMemV4I32 0
; MIR-DAG: Callseq_End {{[0-9]+}}
; MIR-BEFORE-DAG: %4:int32regs = ProxyRegI32 killed %0
; MIR-BEFORE-DAG: %5:int32regs = ProxyRegI32 killed %1
; MIR-BEFORE-DAG: %6:int32regs = ProxyRegI32 killed %2
; MIR-BEFORE-DAG: %7:int32regs = ProxyRegI32 killed %3
; MIR-BEFORE-DAG: StoreRetvalV4I32 killed %4, killed %5, killed %6, killed %7, 0
; MIR-AFTER-DAG: StoreRetvalV4I32 killed %0, killed %1, killed %2, killed %3, 0
%ret = call <4 x i32> @callee_vec_i32()
ret <4 x i32> %ret
}

View File

@ -0,0 +1,183 @@
; RUN: llc -march=nvptx64 -stop-before=nvptx-proxyreg-erasure < %s 2>&1 \
; RUN: | llc -x mir -march=nvptx64 -start-before=nvptx-proxyreg-erasure 2>&1 \
; RUN: | FileCheck %s --check-prefix=PTX --check-prefix=PTX-WITH
; RUN: llc -march=nvptx64 -stop-before=nvptx-proxyreg-erasure < %s 2>&1 \
; RUN: | llc -x mir -march=nvptx64 -start-after=nvptx-proxyreg-erasure 2>&1 \
; RUN: | FileCheck %s --check-prefix=PTX --check-prefix=PTX-WITHOUT
; Thorough testing of ProxyRegErasure: PTX assembly with and without the pass.
declare i1 @callee_i1()
define i1 @check_i1() {
; PTX-LABEL: check_i1
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.b32 [[LD:%r[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b32 [[PROXY:%r[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: and.b32 [[RES:%r[0-9]+]], [[PROXY]], 1;
; PTX-WITH-DAG: and.b32 [[RES:%r[0-9]+]], [[LD]], 1;
; PTX-DAG: st.param.b32 [func_retval0+0], [[RES]];
%ret = call i1 @callee_i1()
ret i1 %ret
}
declare i16 @callee_i16()
define i16 @check_i16() {
; PTX-LABEL: check_i16
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.b32 [[LD:%r[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b32 [[PROXY:%r[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: and.b32 [[RES:%r[0-9]+]], [[PROXY]], 65535;
; PTX-WITH-DAG: and.b32 [[RES:%r[0-9]+]], [[LD]], 65535;
; PTX-DAG: st.param.b32 [func_retval0+0], [[RES]];
%ret = call i16 @callee_i16()
ret i16 %ret
}
declare i32 @callee_i32()
define i32 @check_i32() {
; PTX-LABEL: check_i32
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.b32 [[LD:%r[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b32 [[PROXY:%r[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: st.param.b32 [func_retval0+0], [[PROXY]];
; PTX-WITH-DAG: st.param.b32 [func_retval0+0], [[LD]];
%ret = call i32 @callee_i32()
ret i32 %ret
}
declare i64 @callee_i64()
define i64 @check_i64() {
; PTX-LABEL: check_i64
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.b64 [[LD:%rd[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b64 [[PROXY:%rd[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: st.param.b64 [func_retval0+0], [[PROXY]];
; PTX-WITH-DAG: st.param.b64 [func_retval0+0], [[LD]];
%ret = call i64 @callee_i64()
ret i64 %ret
}
declare i128 @callee_i128()
define i128 @check_i128() {
; PTX-LABEL: check_i128
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.v2.b64 {[[LD0:%rd[0-9]+]], [[LD1:%rd[0-9]+]]}, [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b64 [[PROXY0:%rd[0-9]+]], [[LD0]];
; PTX-WITHOUT-DAG: mov.b64 [[PROXY1:%rd[0-9]+]], [[LD1]];
; PTX-WITHOUT-DAG: st.param.v2.b64 [func_retval0+0], {[[PROXY0]], [[PROXY1]]};
; PTX-WITH-DAG: st.param.v2.b64 [func_retval0+0], {[[LD0]], [[LD1]]};
%ret = call i128 @callee_i128()
ret i128 %ret
}
declare half @callee_f16()
define half @check_f16() {
; PTX-LABEL: check_f16
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.b16 [[LD:%h[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b16 [[PROXY:%h[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: st.param.b16 [func_retval0+0], [[PROXY]];
; PTX-WITH-DAG: st.param.b16 [func_retval0+0], [[LD]];
%ret = call half @callee_f16()
ret half %ret
}
declare float @callee_f32()
define float @check_f32() {
; PTX-LABEL: check_f32
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.f32 [[LD:%f[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.f32 [[PROXY:%f[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: st.param.f32 [func_retval0+0], [[PROXY]];
; PTX-WITH-DAG: st.param.f32 [func_retval0+0], [[LD]];
%ret = call float @callee_f32()
ret float %ret
}
declare double @callee_f64()
define double @check_f64() {
; PTX-LABEL: check_f64
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.f64 [[LD:%fd[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.f64 [[PROXY:%fd[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: st.param.f64 [func_retval0+0], [[PROXY]];
; PTX-WITH-DAG: st.param.f64 [func_retval0+0], [[LD]];
%ret = call double @callee_f64()
ret double %ret
}
declare <4 x i32> @callee_vec_i32()
define <4 x i32> @check_vec_i32() {
; PTX-LABEL: check_vec_i32
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.v4.b32 {[[LD0:%r[0-9]+]], [[LD1:%r[0-9]+]], [[LD2:%r[0-9]+]], [[LD3:%r[0-9]+]]}, [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b32 [[PROXY0:%r[0-9]+]], [[LD0]];
; PTX-WITHOUT-DAG: mov.b32 [[PROXY1:%r[0-9]+]], [[LD1]];
; PTX-WITHOUT-DAG: mov.b32 [[PROXY2:%r[0-9]+]], [[LD2]];
; PTX-WITHOUT-DAG: mov.b32 [[PROXY3:%r[0-9]+]], [[LD3]];
; PTX-WITHOUT-DAG: st.param.v4.b32 [func_retval0+0], {[[PROXY0]], [[PROXY1]], [[PROXY2]], [[PROXY3]]};
; PTX-WITH-DAG: st.param.v4.b32 [func_retval0+0], {[[LD0]], [[LD1]], [[LD2]], [[LD3]]};
%ret = call <4 x i32> @callee_vec_i32()
ret <4 x i32> %ret
}
declare <2 x half> @callee_vec_f16()
define <2 x half> @check_vec_f16() {
; PTX-LABEL: check_vec_f16
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.b32 [[LD:%hh[0-9]+]], [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.b32 [[PROXY:%hh[0-9]+]], [[LD]];
; PTX-WITHOUT-DAG: st.param.b32 [func_retval0+0], [[PROXY]];
; PTX-WITH-DAG: st.param.b32 [func_retval0+0], [[LD]];
%ret = call <2 x half> @callee_vec_f16()
ret <2 x half> %ret
}
declare <2 x double> @callee_vec_f64()
define <2 x double> @check_vec_f64() {
; PTX-LABEL: check_vec_f64
; PTX-DAG: { // callseq {{[0-9]+}}, {{[0-9]+}}
; PTX-DAG: ld.param.v2.f64 {[[LD0:%fd[0-9]+]], [[LD1:%fd[0-9]+]]}, [retval0+0];
; PTX-DAG: } // callseq {{[0-9]+}}
; PTX-WITHOUT-DAG: mov.f64 [[PROXY0:%fd[0-9]+]], [[LD0]];
; PTX-WITHOUT-DAG: mov.f64 [[PROXY1:%fd[0-9]+]], [[LD1]];
; PTX-WITHOUT-DAG: st.param.v2.f64 [func_retval0+0], {[[PROXY0]], [[PROXY1]]};
; PTX-WITH-DAG: st.param.v2.f64 [func_retval0+0], {[[LD0]], [[LD1]]};
%ret = call <2 x double> @callee_vec_f64()
ret <2 x double> %ret
}

View File

@ -1,10 +0,0 @@
; RUN: not llc < %s -march=nvptx 2>&1 | FileCheck %s
; used to seqfault and now fails with a "Cannot select"
; CHECK: LLVM ERROR: Cannot select: {{t7|0x[0-9a-f]+}}: i32 = ExternalSymbol'__powidf2'
define double @powi() {
%1 = call double @llvm.powi.f64(double 1.000000e+00, i32 undef)
ret double %1
}
declare double @llvm.powi.f64(double, i32) nounwind readnone