[llvm] r261995 - [AMDGPU] Assembler: Basic support for MIMG
Nikolay Haustov via llvm-commits
llvm-commits at lists.llvm.org
Fri Feb 26 01:51:05 PST 2016
Author: nhaustov
Date: Fri Feb 26 03:51:05 2016
New Revision: 261995
URL: http://llvm.org/viewvc/llvm-project?rev=261995&view=rev
Log:
[AMDGPU] Assembler: Basic support for MIMG
Add parsing and printing of image operands. Matches legacy sp3 assembler.
Change image instruction order to have data/image/sampler operands in the beginning. This is needed because optional operands in MC are always last.
Update SITargetLowering for new order.
Add basic MC test.
Update CodeGen tests.
Review: http://reviews.llvm.org/D17574
Added:
llvm/trunk/test/MC/AMDGPU/mimg.s
Modified:
llvm/trunk/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.cpp
llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.h
llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td
llvm/trunk/lib/Target/AMDGPU/SIInstructions.td
llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.gather4.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.getlod.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample-masked.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.o.ll
llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.image.ll
llvm/trunk/test/CodeGen/AMDGPU/sgpr-copy.ll
llvm/trunk/test/CodeGen/AMDGPU/si-lod-bias.ll
llvm/trunk/test/CodeGen/AMDGPU/split-smrd.ll
Modified: llvm/trunk/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp Fri Feb 26 03:51:05 2016
@@ -67,7 +67,12 @@ public:
ImmTySLC,
ImmTyTFE,
ImmTyClamp,
- ImmTyOMod
+ ImmTyOMod,
+ ImmTyDMask,
+ ImmTyUNorm,
+ ImmTyDA,
+ ImmTyR128,
+ ImmTyLWE,
};
struct TokOp {
@@ -194,14 +199,31 @@ public:
return Kind == Register || isInlinableImm();
}
+ bool isImmTy(ImmTy ImmT) const {
+ return isImm() && Imm.Type == ImmT;
+ }
+
bool isClamp() const {
- return isImm() && Imm.Type == ImmTyClamp;
+ return isImmTy(ImmTyClamp);
}
bool isOMod() const {
- return isImm() && Imm.Type == ImmTyOMod;
+ return isImmTy(ImmTyOMod);
+ }
+
+ bool isImmModifier() const {
+ return Kind == Immediate && Imm.Type != ImmTyNone;
}
+ bool isDMask() const {
+ return isImmTy(ImmTyDMask);
+ }
+
+ bool isUNorm() const { return isImmTy(ImmTyUNorm); }
+ bool isDA() const { return isImmTy(ImmTyDA); }
+ bool isR128() const { return isImmTy(ImmTyUNorm); }
+ bool isLWE() const { return isImmTy(ImmTyLWE); }
+
bool isMod() const {
return isClamp() || isOMod();
}
@@ -497,13 +519,17 @@ public:
OperandMatchResultTy parseDMask(OperandVector &Operands);
OperandMatchResultTy parseUNorm(OperandVector &Operands);
+ OperandMatchResultTy parseDA(OperandVector &Operands);
OperandMatchResultTy parseR128(OperandVector &Operands);
+ OperandMatchResultTy parseLWE(OperandVector &Operands);
void cvtId(MCInst &Inst, const OperandVector &Operands);
void cvtVOP3_2_mod(MCInst &Inst, const OperandVector &Operands);
void cvtVOP3_2_nomod(MCInst &Inst, const OperandVector &Operands);
void cvtVOP3_only(MCInst &Inst, const OperandVector &Operands);
void cvtVOP3(MCInst &Inst, const OperandVector &Operands);
+
+ void cvtMIMG(MCInst &Inst, const OperandVector &Operands);
OperandMatchResultTy parseVOP3OptionalOps(OperandVector &Operands);
};
@@ -1751,17 +1777,27 @@ void AMDGPUAsmParser::cvtMubuf(MCInst &I
AMDGPUAsmParser::OperandMatchResultTy
AMDGPUAsmParser::parseDMask(OperandVector &Operands) {
- return parseIntWithPrefix("dmask", Operands);
+ return parseIntWithPrefix("dmask", Operands, AMDGPUOperand::ImmTyDMask);
}
AMDGPUAsmParser::OperandMatchResultTy
AMDGPUAsmParser::parseUNorm(OperandVector &Operands) {
- return parseNamedBit("unorm", Operands);
+ return parseNamedBit("unorm", Operands, AMDGPUOperand::ImmTyUNorm);
+}
+
+AMDGPUAsmParser::OperandMatchResultTy
+AMDGPUAsmParser::parseDA(OperandVector &Operands) {
+ return parseNamedBit("da", Operands, AMDGPUOperand::ImmTyDA);
}
AMDGPUAsmParser::OperandMatchResultTy
AMDGPUAsmParser::parseR128(OperandVector &Operands) {
- return parseNamedBit("r128", Operands);
+ return parseNamedBit("r128", Operands, AMDGPUOperand::ImmTyR128);
+}
+
+AMDGPUAsmParser::OperandMatchResultTy
+AMDGPUAsmParser::parseLWE(OperandVector &Operands) {
+ return parseNamedBit("lwe", Operands, AMDGPUOperand::ImmTyLWE);
}
//===----------------------------------------------------------------------===//
@@ -1931,6 +1967,34 @@ void AMDGPUAsmParser::cvtVOP3(MCInst &In
}
}
+void AMDGPUAsmParser::cvtMIMG(MCInst &Inst, const OperandVector &Operands) {
+ OptionalImmIndexMap OptionalIdx;
+
+ for (unsigned i = 1, e = Operands.size(); i != e; ++i) {
+ AMDGPUOperand &Op = ((AMDGPUOperand &)*Operands[i]);
+
+ // Add the register arguments
+ if (Op.isRegOrImm()) {
+ Op.addRegOrImmOperands(Inst, 1);
+ continue;
+ } else if (Op.isImmModifier()) {
+ OptionalIdx[Op.getImmTy()] = i;
+ } else {
+ assert(false);
+ }
+ }
+
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyDMask);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyUNorm);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyGLC);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyDA);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyR128);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyTFE);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyLWE);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTySLC);
+}
+
+
/// Force static initialization.
extern "C" void LLVMInitializeAMDGPUAsmParser() {
RegisterMCAsmParser<AMDGPUAsmParser> A(TheAMDGPUTarget);
Modified: llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.cpp?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.cpp Fri Feb 26 03:51:05 2016
@@ -53,22 +53,25 @@ void AMDGPUInstPrinter::printU16ImmDecOp
O << formatDec(MI->getOperand(OpNo).getImm() & 0xffff);
}
+void AMDGPUInstPrinter::printNamedBit(const MCInst* MI, unsigned OpNo, raw_ostream& O, const char* BitName) {
+ if (MI->getOperand(OpNo).getImm()) {
+ O << " " << BitName;
+ }
+}
+
void AMDGPUInstPrinter::printOffen(const MCInst *MI, unsigned OpNo,
raw_ostream &O) {
- if (MI->getOperand(OpNo).getImm())
- O << " offen";
+ printNamedBit(MI, OpNo, O, "offen");
}
void AMDGPUInstPrinter::printIdxen(const MCInst *MI, unsigned OpNo,
raw_ostream &O) {
- if (MI->getOperand(OpNo).getImm())
- O << " idxen";
+ printNamedBit(MI, OpNo, O, "idxen");
}
void AMDGPUInstPrinter::printAddr64(const MCInst *MI, unsigned OpNo,
raw_ostream &O) {
- if (MI->getOperand(OpNo).getImm())
- O << " addr64";
+ printNamedBit(MI, OpNo, O, "addr64");
}
void AMDGPUInstPrinter::printMBUFOffset(const MCInst *MI, unsigned OpNo,
@@ -106,26 +109,50 @@ void AMDGPUInstPrinter::printDSOffset1(c
void AMDGPUInstPrinter::printGDS(const MCInst *MI, unsigned OpNo,
raw_ostream &O) {
- if (MI->getOperand(OpNo).getImm())
- O << " gds";
+ printNamedBit(MI, OpNo, O, "gds");
}
void AMDGPUInstPrinter::printGLC(const MCInst *MI, unsigned OpNo,
raw_ostream &O) {
- if (MI->getOperand(OpNo).getImm())
- O << " glc";
+ printNamedBit(MI, OpNo, O, "glc");
}
void AMDGPUInstPrinter::printSLC(const MCInst *MI, unsigned OpNo,
raw_ostream &O) {
- if (MI->getOperand(OpNo).getImm())
- O << " slc";
+ printNamedBit(MI, OpNo, O, "slc");
}
void AMDGPUInstPrinter::printTFE(const MCInst *MI, unsigned OpNo,
raw_ostream &O) {
- if (MI->getOperand(OpNo).getImm())
- O << " tfe";
+ printNamedBit(MI, OpNo, O, "tfe");
+}
+
+void AMDGPUInstPrinter::printDMask(const MCInst *MI, unsigned OpNo,
+ raw_ostream &O) {
+ if (MI->getOperand(OpNo).getImm()) {
+ O << " dmask:";
+ printU16ImmOperand(MI, OpNo, O);
+ }
+}
+
+void AMDGPUInstPrinter::printUNorm(const MCInst *MI, unsigned OpNo,
+ raw_ostream &O) {
+ printNamedBit(MI, OpNo, O, "unorm");
+}
+
+void AMDGPUInstPrinter::printDA(const MCInst *MI, unsigned OpNo,
+ raw_ostream &O) {
+ printNamedBit(MI, OpNo, O, "da");
+}
+
+void AMDGPUInstPrinter::printR128(const MCInst *MI, unsigned OpNo,
+ raw_ostream &O) {
+ printNamedBit(MI, OpNo, O, "r128");
+}
+
+void AMDGPUInstPrinter::printLWE(const MCInst *MI, unsigned OpNo,
+ raw_ostream &O) {
+ printNamedBit(MI, OpNo, O, "lwe");
}
void AMDGPUInstPrinter::printRegOperand(unsigned reg, raw_ostream &O,
Modified: llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.h?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.h (original)
+++ llvm/trunk/lib/Target/AMDGPU/InstPrinter/AMDGPUInstPrinter.h Fri Feb 26 03:51:05 2016
@@ -38,6 +38,7 @@ private:
void printU8ImmDecOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printU16ImmDecOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printU32ImmOperand(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+ void printNamedBit(const MCInst* MI, unsigned OpNo, raw_ostream& O, const char* BitName);
void printOffen(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printIdxen(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printAddr64(const MCInst *MI, unsigned OpNo, raw_ostream &O);
@@ -49,6 +50,11 @@ private:
void printGLC(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printSLC(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printTFE(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+ void printDMask(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+ void printUNorm(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+ void printDA(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+ void printR128(const MCInst *MI, unsigned OpNo, raw_ostream &O);
+ void printLWE(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printRegOperand(unsigned RegNo, raw_ostream &O);
void printVOPDst(const MCInst *MI, unsigned OpNo, raw_ostream &O);
void printImmediate32(uint32_t I, raw_ostream &O);
Modified: llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp Fri Feb 26 03:51:05 2016
@@ -2657,7 +2657,8 @@ void SITargetLowering::adjustWritemask(M
SelectionDAG &DAG) const {
SDNode *Users[4] = { };
unsigned Lane = 0;
- unsigned OldDmask = Node->getConstantOperandVal(0);
+ unsigned DmaskIdx = (Node->getNumOperands() - Node->getNumValues() == 9) ? 2 : 3;
+ unsigned OldDmask = Node->getConstantOperandVal(DmaskIdx);
unsigned NewDmask = 0;
// Try to figure out the used register components
@@ -2697,8 +2698,9 @@ void SITargetLowering::adjustWritemask(M
// Adjust the writemask in the node
std::vector<SDValue> Ops;
+ Ops.insert(Ops.end(), Node->op_begin(), Node->op_begin() + DmaskIdx);
Ops.push_back(DAG.getTargetConstant(NewDmask, SDLoc(Node), MVT::i32));
- Ops.insert(Ops.end(), Node->op_begin() + 1, Node->op_end());
+ Ops.insert(Ops.end(), Node->op_begin() + DmaskIdx + 1, Node->op_end());
Node = (MachineSDNode*)DAG.UpdateNodeOperands(Node, Ops);
// If we only got one lane, replace it with a copy
@@ -2796,7 +2798,8 @@ void SITargetLowering::AdjustInstrPostIn
if (TII->isMIMG(*MI)) {
unsigned VReg = MI->getOperand(0).getReg();
- unsigned Writemask = MI->getOperand(1).getImm();
+ unsigned DmaskIdx = MI->getNumOperands() == 12 ? 3 : 4;
+ unsigned Writemask = MI->getOperand(DmaskIdx).getImm();
unsigned BitsSet = 0;
for (unsigned i = 0; i < 4; ++i)
BitsSet += Writemask & (1 << i) ? 1 : 0;
Modified: llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td Fri Feb 26 03:51:05 2016
@@ -533,9 +533,30 @@ def SMRDLiteralOffsetMatchClass : SMRDOf
class OptionalImmAsmOperand <string OpName> : AsmOperandClass {
let Name = "Imm"#OpName;
let PredicateMethod = "isImm";
+ let RenderMethod = "addImmOperands";
let IsOptional = 1;
}
+def DMaskMatchClass : AsmOperandClass {
+ let Name = "DMask";
+ let PredicateMethod = "isDMask";
+ let ParserMethod = "parseDMask";
+ let RenderMethod = "addImmOperands";
+ let IsOptional = 1;
+}
+
+class NamedBitMatchClass<string BitName> : AsmOperandClass {
+ let Name = "Imm"#BitName;
+ let PredicateMethod = "is"#BitName;
+ let ParserMethod = "parse"#BitName;
+ let RenderMethod = "addImmOperands";
+ let IsOptional = 1;
+}
+
+class NamedBitOperand<string BitName> : Operand<i1> {
+ let PrintMethod = "print"#BitName;
+}
+
let OperandType = "OPERAND_IMMEDIATE" in {
def offen : Operand<i1> {
@@ -622,8 +643,30 @@ def smrd_literal_offset : Operand <i32>
let ParserMatchClass = SMRDLiteralOffsetMatchClass;
}
+def dmask : Operand <i32> {
+ let PrintMethod = "printDMask";
+ let ParserMatchClass = DMaskMatchClass;
+}
+
+def unorm : NamedBitOperand<"UNorm"> {
+ let ParserMatchClass = NamedBitMatchClass<"UNorm">;
+}
+
+def da : NamedBitOperand<"DA"> {
+ let ParserMatchClass = NamedBitMatchClass<"DA">;
+}
+
+def r128 : NamedBitOperand<"R128"> {
+ let ParserMatchClass = NamedBitMatchClass<"R128">;
+}
+
+def lwe : NamedBitOperand<"LWE"> {
+ let ParserMatchClass = NamedBitMatchClass<"LWE">;
+}
+
} // End OperandType = "OPERAND_IMMEDIATE"
+
def VOPDstS64 : VOPDstOperand <SReg_64>;
//===----------------------------------------------------------------------===//
@@ -2923,6 +2966,7 @@ class MIMG_Helper <bits<7> op, dag outs,
let hasPostISelHook = 1;
let DecoderNamespace = dns;
let isAsmParserOnly = !if(!eq(dns,""), 1, 0);
+ let AsmMatchConverter = "cvtMIMG";
}
class MIMG_NoSampler_Helper <bits<7> op, string asm,
@@ -2931,11 +2975,10 @@ class MIMG_NoSampler_Helper <bits<7> op,
string dns=""> : MIMG_Helper <
op,
(outs dst_rc:$vdata),
- (ins i32imm:$dmask, i1imm:$unorm, i1imm:$glc, i1imm:$da, i1imm:$r128,
- i1imm:$tfe, i1imm:$lwe, i1imm:$slc, addr_rc:$vaddr,
- SReg_256:$srsrc),
- asm#" $vdata, $dmask, $unorm, $glc, $da, $r128,"
- #" $tfe, $lwe, $slc, $vaddr, $srsrc",
+ (ins addr_rc:$vaddr, SReg_256:$srsrc,
+ dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
+ r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
+ asm#" $vdata, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da",
dns> {
let ssamp = 0;
}
@@ -2964,11 +3007,11 @@ class MIMG_Store_Helper <bits<7> op, str
RegisterClass addr_rc> : MIMG_Helper <
op,
(outs),
- (ins data_rc:$vdata, i32imm:$dmask, i1imm:$unorm, i1imm:$glc, i1imm:$da, i1imm:$r128,
- i1imm:$tfe, i1imm:$lwe, i1imm:$slc, addr_rc:$vaddr,
- SReg_256:$srsrc),
- asm#" $vdata, $dmask, $unorm, $glc, $da, $r128,"
- #" $tfe, $lwe, $slc, $vaddr, $srsrc"> {
+ (ins data_rc:$vdata, addr_rc:$vaddr, SReg_256:$srsrc,
+ dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
+ r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
+ asm#" $vdata, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da"
+ > {
let ssamp = 0;
let mayLoad = 1; // TableGen requires this for matching with the intrinsics
let mayStore = 1;
@@ -3001,11 +3044,10 @@ class MIMG_Sampler_Helper <bits<7> op, s
string dns=""> : MIMG_Helper <
op,
(outs dst_rc:$vdata),
- (ins i32imm:$dmask, i1imm:$unorm, i1imm:$glc, i1imm:$da, i1imm:$r128,
- i1imm:$tfe, i1imm:$lwe, i1imm:$slc, src_rc:$vaddr,
- SReg_256:$srsrc, SReg_128:$ssamp),
- asm#" $vdata, $dmask, $unorm, $glc, $da, $r128,"
- #" $tfe, $lwe, $slc, $vaddr, $srsrc, $ssamp",
+ (ins src_rc:$vaddr, SReg_256:$srsrc, SReg_128:$ssamp,
+ dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
+ r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
+ asm#" $vdata, $vaddr, $srsrc, $ssamp$dmask$unorm$glc$slc$r128$tfe$lwe$da",
dns> {
let WQM = wqm;
}
@@ -3040,11 +3082,10 @@ class MIMG_Gather_Helper <bits<7> op, st
RegisterClass src_rc, int wqm> : MIMG <
op,
(outs dst_rc:$vdata),
- (ins i32imm:$dmask, i1imm:$unorm, i1imm:$glc, i1imm:$da, i1imm:$r128,
- i1imm:$tfe, i1imm:$lwe, i1imm:$slc, src_rc:$vaddr,
- SReg_256:$srsrc, SReg_128:$ssamp),
- asm#" $vdata, $dmask, $unorm, $glc, $da, $r128,"
- #" $tfe, $lwe, $slc, $vaddr, $srsrc, $ssamp",
+ (ins src_rc:$vaddr, SReg_256:$srsrc, SReg_128:$ssamp,
+ dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
+ r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
+ asm#" $vdata, $vaddr, $srsrc, $ssamp$dmask$unorm$glc$slc$r128$tfe$lwe$da",
[]> {
let mayLoad = 1;
let mayStore = 0;
Modified: llvm/trunk/lib/Target/AMDGPU/SIInstructions.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIInstructions.td?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIInstructions.td (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIInstructions.td Fri Feb 26 03:51:05 2016
@@ -2215,9 +2215,9 @@ def : Pat <
class SampleRawPattern<SDPatternOperator name, MIMG opcode, ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, v4i32:$sampler, i32:$dmask, i32:$unorm,
i32:$r128, i32:$da, i32:$glc, i32:$slc, i32:$tfe, i32:$lwe),
- (opcode (as_i32imm $dmask), (as_i1imm $unorm), (as_i1imm $glc), (as_i1imm $da),
- (as_i1imm $r128), (as_i1imm $tfe), (as_i1imm $lwe), (as_i1imm $slc),
- $addr, $rsrc, $sampler)
+ (opcode $addr, $rsrc, $sampler,
+ (as_i32imm $dmask), (as_i1imm $unorm), (as_i1imm $glc), (as_i1imm $slc),
+ (as_i1imm $r128), (as_i1imm $tfe), (as_i1imm $lwe), (as_i1imm $da))
>;
multiclass SampleRawPatterns<SDPatternOperator name, string opcode> {
@@ -2232,9 +2232,9 @@ multiclass SampleRawPatterns<SDPatternOp
class ImagePattern<SDPatternOperator name, MIMG opcode, ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, imm:$dmask, imm:$unorm,
imm:$r128, imm:$da, imm:$glc, imm:$slc, imm:$tfe, imm:$lwe),
- (opcode (as_i32imm $dmask), (as_i1imm $unorm), (as_i1imm $glc), (as_i1imm $da),
- (as_i1imm $r128), (as_i1imm $tfe), (as_i1imm $lwe), (as_i1imm $slc),
- $addr, $rsrc)
+ (opcode $addr, $rsrc,
+ (as_i32imm $dmask), (as_i1imm $unorm), (as_i1imm $glc), (as_i1imm $slc),
+ (as_i1imm $r128), (as_i1imm $tfe), (as_i1imm $lwe), (as_i1imm $da))
>;
multiclass ImagePatterns<SDPatternOperator name, string opcode> {
@@ -2246,8 +2246,9 @@ multiclass ImagePatterns<SDPatternOperat
class ImageLoadPattern<SDPatternOperator name, MIMG opcode, ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, imm:$dmask, imm:$r128, imm:$da, imm:$glc,
imm:$slc),
- (opcode (as_i32imm $dmask), 1, (as_i1imm $glc), (as_i1imm $da),
- (as_i1imm $r128), 0, 0, (as_i1imm $slc), $addr, $rsrc)
+ (opcode $addr, $rsrc,
+ (as_i32imm $dmask), 1, (as_i1imm $glc), (as_i1imm $slc),
+ (as_i1imm $r128), 0, 0, (as_i1imm $da))
>;
multiclass ImageLoadPatterns<SDPatternOperator name, string opcode> {
@@ -2259,8 +2260,9 @@ multiclass ImageLoadPatterns<SDPatternOp
class ImageStorePattern<SDPatternOperator name, MIMG opcode, ValueType vt> : Pat <
(name v4f32:$data, vt:$addr, v8i32:$rsrc, i32:$dmask, imm:$r128, imm:$da,
imm:$glc, imm:$slc),
- (opcode $data, (as_i32imm $dmask), 1, (as_i1imm $glc), (as_i1imm $da),
- (as_i1imm $r128), 0, 0, (as_i1imm $slc), $addr, $rsrc)
+ (opcode $data, $addr, $rsrc,
+ (as_i32imm $dmask), 1, (as_i1imm $glc), (as_i1imm $slc),
+ (as_i1imm $r128), 0, 0, (as_i1imm $da))
>;
multiclass ImageStorePatterns<SDPatternOperator name, string opcode> {
@@ -2373,34 +2375,34 @@ defm : ImageStorePatterns<int_amdgcn_ima
/* SIsample for simple 1D texture lookup */
def : Pat <
(SIsample i32:$addr, v8i32:$rsrc, v4i32:$sampler, imm),
- (IMAGE_SAMPLE_V4_V1 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
+ (IMAGE_SAMPLE_V4_V1 $addr, $rsrc, $sampler, 0xf, 0, 0, 0, 0, 0, 0, 0)
>;
class SamplePattern<SDNode name, MIMG opcode, ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, v4i32:$sampler, imm),
- (opcode 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
+ (opcode $addr, $rsrc, $sampler, 0xf, 0, 0, 0, 0, 0, 0, 0)
>;
class SampleRectPattern<SDNode name, MIMG opcode, ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, v4i32:$sampler, TEX_RECT),
- (opcode 0xf, 1, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
+ (opcode $addr, $rsrc, $sampler, 0xf, 1, 0, 0, 0, 0, 0, 0)
>;
class SampleArrayPattern<SDNode name, MIMG opcode, ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, v4i32:$sampler, TEX_ARRAY),
- (opcode 0xf, 0, 0, 1, 0, 0, 0, 0, $addr, $rsrc, $sampler)
+ (opcode $addr, $rsrc, $sampler, 0xf, 0, 0, 0, 0, 0, 0, 1)
>;
class SampleShadowPattern<SDNode name, MIMG opcode,
ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, v4i32:$sampler, TEX_SHADOW),
- (opcode 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
+ (opcode $addr, $rsrc, $sampler, 0xf, 0, 0, 0, 0, 0, 0, 0)
>;
class SampleShadowArrayPattern<SDNode name, MIMG opcode,
ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, v4i32:$sampler, TEX_SHADOW_ARRAY),
- (opcode 0xf, 0, 0, 1, 0, 0, 0, 0, $addr, $rsrc, $sampler)
+ (opcode $addr, $rsrc, $sampler, 0xf, 0, 0, 0, 0, 0, 0, 1)
>;
/* SIsample* for texture lookups consuming more address parameters */
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.gather4.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.gather4.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.gather4.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.gather4.ll Fri Feb 26 03:51:05 2016
@@ -2,7 +2,7 @@
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}gather4_v2:
-;CHECK: image_gather4 {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4 {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_v2() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.v2i32(<2 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -15,7 +15,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4:
-;CHECK: image_gather4 {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4 {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -28,7 +28,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_cl:
-;CHECK: image_gather4_cl {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -41,7 +41,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_l:
-;CHECK: image_gather4_l {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_l() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.l.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -54,7 +54,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_b:
-;CHECK: image_gather4_b {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_b() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.b.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -67,7 +67,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_b_cl:
-;CHECK: image_gather4_b_cl {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_b_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.b.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -80,7 +80,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_b_cl_v8:
-;CHECK: image_gather4_b_cl {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_b_cl_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.b.cl.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -93,7 +93,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_lz_v2:
-;CHECK: image_gather4_lz {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_lz_v2() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.lz.v2i32(<2 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -106,7 +106,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_lz:
-;CHECK: image_gather4_lz {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_lz() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.lz.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -121,7 +121,7 @@ main_body:
;CHECK-LABEL: {{^}}gather4_o:
-;CHECK: image_gather4_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -134,7 +134,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_cl_o:
-;CHECK: image_gather4_cl_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_cl_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -147,7 +147,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_cl_o_v8:
-;CHECK: image_gather4_cl_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_cl_o_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.cl.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -160,7 +160,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_l_o:
-;CHECK: image_gather4_l_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_l_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.l.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -173,7 +173,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_l_o_v8:
-;CHECK: image_gather4_l_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_l_o_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.l.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -186,7 +186,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_b_o:
-;CHECK: image_gather4_b_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_b_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.b.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -199,7 +199,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_b_o_v8:
-;CHECK: image_gather4_b_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_b_o_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.b.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -212,7 +212,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_b_cl_o:
-;CHECK: image_gather4_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_b_cl_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.b.cl.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -225,7 +225,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_lz_o:
-;CHECK: image_gather4_lz_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_lz_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.lz.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -240,7 +240,7 @@ main_body:
;CHECK-LABEL: {{^}}gather4_c:
-;CHECK: image_gather4_c {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -253,7 +253,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_cl:
-;CHECK: image_gather4_c_cl {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -266,7 +266,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_cl_v8:
-;CHECK: image_gather4_c_cl {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_cl_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.cl.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -279,7 +279,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_l:
-;CHECK: image_gather4_c_l {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_l() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.l.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -292,7 +292,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_l_v8:
-;CHECK: image_gather4_c_l {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_l_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.l.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -305,7 +305,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_b:
-;CHECK: image_gather4_c_b {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_b() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.b.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -318,7 +318,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_b_v8:
-;CHECK: image_gather4_c_b {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_b_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.b.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -331,7 +331,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_b_cl:
-;CHECK: image_gather4_c_b_cl {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_b_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.b.cl.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -344,7 +344,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_lz:
-;CHECK: image_gather4_c_lz {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_lz() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.lz.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -359,7 +359,7 @@ main_body:
;CHECK-LABEL: {{^}}gather4_c_o:
-;CHECK: image_gather4_c_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -372,7 +372,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_o_v8:
-;CHECK: image_gather4_c_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_o_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -385,7 +385,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_cl_o:
-;CHECK: image_gather4_c_cl_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_cl_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.cl.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -398,7 +398,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_l_o:
-;CHECK: image_gather4_c_l_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_l_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.l.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -411,7 +411,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_b_o:
-;CHECK: image_gather4_c_b_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_b_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.b.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -424,7 +424,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_b_cl_o:
-;CHECK: image_gather4_c_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_b_cl_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.b.cl.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -437,7 +437,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_lz_o:
-;CHECK: image_gather4_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_lz_o() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.lz.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -450,7 +450,7 @@ main_body:
}
;CHECK-LABEL: {{^}}gather4_c_lz_o_v8:
-;CHECK: image_gather4_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_gather4_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
define void @gather4_c_lz_o_v8() #0 {
main_body:
%r = call <4 x float> @llvm.SI.gather4.c.lz.o.v8i32(<8 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.getlod.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.getlod.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.getlod.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.getlod.ll Fri Feb 26 03:51:05 2016
@@ -2,7 +2,7 @@
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}getlod:
-;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, 3, 0, 0, -1, 0, 0, 0, 0, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x3 da
define void @getlod() #0 {
main_body:
%r = call <4 x float> @llvm.SI.getlod.i32(i32 undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -13,7 +13,7 @@ main_body:
}
;CHECK-LABEL: {{^}}getlod_v2:
-;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, 3, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x3 da
define void @getlod_v2() #0 {
main_body:
%r = call <4 x float> @llvm.SI.getlod.v2i32(<2 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
@@ -24,7 +24,7 @@ main_body:
}
;CHECK-LABEL: {{^}}getlod_v4:
-;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, 3, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x3 da
define void @getlod_v4() #0 {
main_body:
%r = call <4 x float> @llvm.SI.getlod.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.ll Fri Feb 26 03:51:05 2016
@@ -2,7 +2,7 @@
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}image_load:
-;CHECK: image_load {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_load {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @image_load() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.load.v4i32(<4 x i32> undef, <8 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -15,7 +15,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_load_mip:
-;CHECK: image_load_mip {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_load_mip {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @image_load_mip() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.load.mip.v4i32(<4 x i32> undef, <8 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -28,7 +28,7 @@ main_body:
}
;CHECK-LABEL: {{^}}getresinfo:
-;CHECK: image_get_resinfo {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_get_resinfo {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @getresinfo() #0 {
main_body:
%r = call <4 x float> @llvm.SI.getresinfo.i32(i32 undef, <8 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample-masked.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample-masked.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample-masked.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample-masked.ll Fri Feb 26 03:51:05 2016
@@ -2,7 +2,7 @@
;RUN: llc < %s -march=amdgcn -mcpu=tonga | FileCheck %s
; CHECK-LABEL: {{^}}v1:
-; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 13
+; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xd
define void @v1(i32 %a1) #0 {
entry:
%0 = insertelement <1 x i32> undef, i32 %a1, i32 0
@@ -15,7 +15,7 @@ entry:
}
; CHECK-LABEL: {{^}}v2:
-; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 11
+; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xb
define void @v2(i32 %a1) #0 {
entry:
%0 = insertelement <1 x i32> undef, i32 %a1, i32 0
@@ -28,7 +28,7 @@ entry:
}
; CHECK-LABEL: {{^}}v3:
-; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 14
+; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xe
define void @v3(i32 %a1) #0 {
entry:
%0 = insertelement <1 x i32> undef, i32 %a1, i32 0
@@ -41,7 +41,7 @@ entry:
}
; CHECK-LABEL: {{^}}v4:
-; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 7
+; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x7
define void @v4(i32 %a1) #0 {
entry:
%0 = insertelement <1 x i32> undef, i32 %a1, i32 0
@@ -54,7 +54,7 @@ entry:
}
; CHECK-LABEL: {{^}}v5:
-; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 10
+; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xa
define void @v5(i32 %a1) #0 {
entry:
%0 = insertelement <1 x i32> undef, i32 %a1, i32 0
@@ -66,7 +66,7 @@ entry:
}
; CHECK-LABEL: {{^}}v6:
-; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 6
+; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x6
define void @v6(i32 %a1) #0 {
entry:
%0 = insertelement <1 x i32> undef, i32 %a1, i32 0
@@ -78,7 +78,7 @@ entry:
}
; CHECK-LABEL: {{^}}v7:
-; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 9
+; CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x9
define void @v7(i32 %a1) #0 {
entry:
%0 = insertelement <1 x i32> undef, i32 %a1, i32 0
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.ll Fri Feb 26 03:51:05 2016
@@ -3,7 +3,7 @@
;CHECK-LABEL: {{^}}sample:
;CHECK: s_wqm
-;CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -17,7 +17,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_cl:
;CHECK: s_wqm
-;CHECK: image_sample_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -31,7 +31,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_d:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_d {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_d {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_d() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.d.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -45,7 +45,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_d_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_d_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_d_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_d_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.d.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -59,7 +59,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_l:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_l {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_l() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.l.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -73,7 +73,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_b:
;CHECK: s_wqm
-;CHECK: image_sample_b {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_b() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.b.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -87,7 +87,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_b_cl:
;CHECK: s_wqm
-;CHECK: image_sample_b_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_b_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.b.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -101,7 +101,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_lz:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_lz {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_lz() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.lz.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -115,7 +115,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_cd:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_cd {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_cd {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_cd() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.cd.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -129,7 +129,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_cd_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_cd_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_cd_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_cd_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.cd.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -143,7 +143,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c:
;CHECK: s_wqm
-;CHECK: image_sample_c {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -157,7 +157,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_cl:
;CHECK: s_wqm
-;CHECK: image_sample_c_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -171,7 +171,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_d:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_d {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_d {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_d() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.d.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -185,7 +185,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_d_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_d_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_d_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_d_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.d.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -199,7 +199,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_l:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_l {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_l() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.l.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -213,7 +213,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_b:
;CHECK: s_wqm
-;CHECK: image_sample_c_b {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_b() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.b.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -227,7 +227,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_b_cl:
;CHECK: s_wqm
-;CHECK: image_sample_c_b_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_b_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.b.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -241,7 +241,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_lz:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_lz {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_lz() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.lz.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -255,7 +255,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_cd:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_cd {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_cd {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_cd() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.cd.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -269,7 +269,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_cd_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_cd_cl {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_cd_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_cd_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.cd.cl.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.o.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.o.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.o.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.SI.image.sample.o.ll Fri Feb 26 03:51:05 2016
@@ -3,7 +3,7 @@
;CHECK-LABEL: {{^}}sample:
;CHECK: s_wqm
-;CHECK: image_sample_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -17,7 +17,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_cl:
;CHECK: s_wqm
-;CHECK: image_sample_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -31,7 +31,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_d:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_d_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_d_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_d() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.d.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -45,7 +45,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_d_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_d_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_d_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_d_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.d.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -59,7 +59,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_l:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_l_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_l() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.l.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -73,7 +73,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_b:
;CHECK: s_wqm
-;CHECK: image_sample_b_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_b() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.b.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -87,7 +87,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_b_cl:
;CHECK: s_wqm
-;CHECK: image_sample_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_b_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.b.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -101,7 +101,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_lz:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_lz_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_lz() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.lz.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -115,7 +115,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_cd:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_cd_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_cd_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_cd() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.cd.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -129,7 +129,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_cd_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_cd_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_cd_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_cd_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.cd.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -143,7 +143,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c:
;CHECK: s_wqm
-;CHECK: image_sample_c_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -157,7 +157,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_cl:
;CHECK: s_wqm
-;CHECK: image_sample_c_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -171,7 +171,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_d:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_d_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_d_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_d() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.d.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -185,7 +185,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_d_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_d_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_d_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_d_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.d.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -199,7 +199,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_l:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_l_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_l() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.l.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -213,7 +213,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_b:
;CHECK: s_wqm
-;CHECK: image_sample_c_b_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_b() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.b.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -227,7 +227,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_b_cl:
;CHECK: s_wqm
-;CHECK: image_sample_c_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_b_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.b.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -241,7 +241,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_lz:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_lz() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.lz.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -255,7 +255,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_cd:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_cd_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_cd_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_cd() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.cd.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
@@ -269,7 +269,7 @@ main_body:
;CHECK-LABEL: {{^}}sample_c_cd_cl:
;CHECK-NOT: s_wqm
-;CHECK: image_sample_c_cd_cl_o {{v\[[0-9]+:[0-9]+\]}}, 15, 0, 0, 0, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
+;CHECK: image_sample_c_cd_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
define void @sample_c_cd_cl() #0 {
main_body:
%r = call <4 x float> @llvm.SI.image.sample.c.cd.cl.o.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
Modified: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.image.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.image.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.image.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.image.ll Fri Feb 26 03:51:05 2016
@@ -2,7 +2,7 @@
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}image_load_v4i32:
-;CHECK: image_load v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v[0:3], s[0:7]
+;CHECK: image_load v[0:3], v[0:3], s[0:7] dmask:0xf unorm
;CHECK: s_waitcnt vmcnt(0)
define <4 x float> @image_load_v4i32(<8 x i32> inreg %rsrc, <4 x i32> %c) #0 {
main_body:
@@ -11,7 +11,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_load_v2i32:
-;CHECK: image_load v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v[0:1], s[0:7]
+;CHECK: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm
;CHECK: s_waitcnt vmcnt(0)
define <4 x float> @image_load_v2i32(<8 x i32> inreg %rsrc, <2 x i32> %c) #0 {
main_body:
@@ -20,7 +20,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_load_i32:
-;CHECK: image_load v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v0, s[0:7]
+;CHECK: image_load v[0:3], v0, s[0:7] dmask:0xf unorm
;CHECK: s_waitcnt vmcnt(0)
define <4 x float> @image_load_i32(<8 x i32> inreg %rsrc, i32 %c) #0 {
main_body:
@@ -29,7 +29,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_load_mip:
-;CHECK: image_load_mip v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v[0:3], s[0:7]
+;CHECK: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm
;CHECK: s_waitcnt vmcnt(0)
define <4 x float> @image_load_mip(<8 x i32> inreg %rsrc, <4 x i32> %c) #0 {
main_body:
@@ -38,7 +38,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_load_1:
-;CHECK: image_load v0, 1, -1, 0, 0, 0, 0, 0, 0, v[0:3], s[0:7]
+;CHECK: image_load v0, v[0:3], s[0:7] dmask:0x1 unorm
;CHECK: s_waitcnt vmcnt(0)
define float @image_load_1(<8 x i32> inreg %rsrc, <4 x i32> %c) #0 {
main_body:
@@ -49,7 +49,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_store_v4i32:
-;CHECK: image_store v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v[4:7], s[0:7]
+;CHECK: image_store v[0:3], v[4:7], s[0:7] dmask:0xf unorm
define void @image_store_v4i32(<8 x i32> inreg %rsrc, <4 x float> %data, <4 x i32> %coords) #0 {
main_body:
call void @llvm.amdgcn.image.store.v4i32(<4 x float> %data, <4 x i32> %coords, <8 x i32> %rsrc, i32 15, i1 0, i1 0, i1 0, i1 0)
@@ -57,7 +57,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_store_v2i32:
-;CHECK: image_store v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v[4:5], s[0:7]
+;CHECK: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm
define void @image_store_v2i32(<8 x i32> inreg %rsrc, <4 x float> %data, <2 x i32> %coords) #0 {
main_body:
call void @llvm.amdgcn.image.store.v2i32(<4 x float> %data, <2 x i32> %coords, <8 x i32> %rsrc, i32 15, i1 0, i1 0, i1 0, i1 0)
@@ -65,7 +65,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_store_i32:
-;CHECK: image_store v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v4, s[0:7]
+;CHECK: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
define void @image_store_i32(<8 x i32> inreg %rsrc, <4 x float> %data, i32 %coords) #0 {
main_body:
call void @llvm.amdgcn.image.store.i32(<4 x float> %data, i32 %coords, <8 x i32> %rsrc, i32 15, i1 0, i1 0, i1 0, i1 0)
@@ -73,7 +73,7 @@ main_body:
}
;CHECK-LABEL: {{^}}image_store_mip:
-;CHECK: image_store_mip v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v[4:7], s[0:7]
+;CHECK: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm
define void @image_store_mip(<8 x i32> inreg %rsrc, <4 x float> %data, <4 x i32> %coords) #0 {
main_body:
call void @llvm.amdgcn.image.store.mip.v4i32(<4 x float> %data, <4 x i32> %coords, <8 x i32> %rsrc, i32 15, i1 0, i1 0, i1 0, i1 0)
@@ -83,11 +83,11 @@ main_body:
; Ideally, the register allocator would avoid the wait here
;
;CHECK-LABEL: {{^}}image_store_wait:
-;CHECK: image_store v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v4, s[0:7]
+;CHECK: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
;CHECK: s_waitcnt vmcnt(0) expcnt(0)
-;CHECK: image_load v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v4, s[8:15]
+;CHECK: image_load v[0:3], v4, s[8:15] dmask:0xf unorm
;CHECK: s_waitcnt vmcnt(0)
-;CHECK: image_store v[0:3], 15, -1, 0, 0, 0, 0, 0, 0, v4, s[16:23]
+;CHECK: image_store v[0:3], v4, s[16:23] dmask:0xf unorm
define void @image_store_wait(<8 x i32> inreg, <8 x i32> inreg, <8 x i32> inreg, <4 x float>, i32) #0 {
main_body:
call void @llvm.amdgcn.image.store.i32(<4 x float> %3, i32 %4, <8 x i32> %0, i32 15, i1 0, i1 0, i1 0, i1 0)
Modified: llvm/trunk/test/CodeGen/AMDGPU/sgpr-copy.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/sgpr-copy.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/sgpr-copy.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/sgpr-copy.ll Fri Feb 26 03:51:05 2016
@@ -364,7 +364,7 @@ bb71:
; Check the the resource descriptor is stored in an sgpr.
; CHECK-LABEL: {{^}}mimg_srsrc_sgpr:
-; CHECK: image_sample v{{[0-9]+}}, 1, 0, 0, 0, 0, 0, 0, 0, v[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}]
+; CHECK: image_sample v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}] dmask:0x1
define void @mimg_srsrc_sgpr([34 x <8 x i32>] addrspace(2)* byval %arg) #0 {
%tid = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
%tmp7 = getelementptr [34 x <8 x i32>], [34 x <8 x i32>] addrspace(2)* %arg, i32 0, i32 %tid
@@ -379,7 +379,7 @@ define void @mimg_srsrc_sgpr([34 x <8 x
; Check the the sampler is stored in an sgpr.
; CHECK-LABEL: {{^}}mimg_ssamp_sgpr:
-; CHECK: image_sample v{{[0-9]+}}, 1, 0, 0, 0, 0, 0, 0, 0, v[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}]
+; CHECK: image_sample v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}] dmask:0x1
define void @mimg_ssamp_sgpr([17 x <4 x i32>] addrspace(2)* byval %arg) #0 {
%tid = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
%tmp7 = getelementptr [17 x <4 x i32>], [17 x <4 x i32>] addrspace(2)* %arg, i32 0, i32 %tid
Modified: llvm/trunk/test/CodeGen/AMDGPU/si-lod-bias.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/si-lod-bias.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/si-lod-bias.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/si-lod-bias.ll Fri Feb 26 03:51:05 2016
@@ -5,7 +5,7 @@
; the wrong register class is used for the REG_SEQUENCE instructions.
; CHECK: {{^}}main:
-; CHECK: image_sample_b v{{\[[0-9]:[0-9]\]}}, 15, 0, 0, 0, 0, 0, 0, 0, v{{\[[0-9]:[0-9]\]}}
+; CHECK: image_sample_b v{{\[[0-9]:[0-9]\]}}, v{{\[[0-9]:[0-9]\]}}, s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}] dmask:0xf
define void @main(<16 x i8> addrspace(2)* inreg %arg, <16 x i8> addrspace(2)* inreg %arg1, <8 x i32> addrspace(2)* inreg %arg2, i32 inreg %arg3, <2 x i32> %arg4, <2 x i32> %arg5, <2 x i32> %arg6, <3 x i32> %arg7, <2 x i32> %arg8, <2 x i32> %arg9, <2 x i32> %arg10, float %arg11, float %arg12, float %arg13, float %arg14, float %arg15, float %arg16, float %arg17, float %arg18, float %arg19) #0 {
main_body:
%tmp = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %arg, i32 0
Modified: llvm/trunk/test/CodeGen/AMDGPU/split-smrd.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/split-smrd.ll?rev=261995&r1=261994&r2=261995&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/split-smrd.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/split-smrd.ll Fri Feb 26 03:51:05 2016
@@ -4,7 +4,7 @@
; Make sure that when we split an smrd instruction in order to move it to
; the VALU, we are also moving its users to the VALU.
; CHECK-LABEL: {{^}}split_smrd_add_worklist:
-; CHECK: image_sample v{{[0-9]+}}, 1, 0, 0, 0, 0, 0, 0, 0, v[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}]
+; CHECK: image_sample v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}] dmask:0x1
define void @split_smrd_add_worklist([34 x <8 x i32>] addrspace(2)* byval %arg) #0 {
bb:
Added: llvm/trunk/test/MC/AMDGPU/mimg.s
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/MC/AMDGPU/mimg.s?rev=261995&view=auto
==============================================================================
--- llvm/trunk/test/MC/AMDGPU/mimg.s (added)
+++ llvm/trunk/test/MC/AMDGPU/mimg.s Fri Feb 26 03:51:05 2016
@@ -0,0 +1,15 @@
+// RUN: llvm-mc -arch=amdgcn -show-encoding %s | FileCheck %s --check-prefix=SICI
+// RUN: llvm-mc -arch=amdgcn -mcpu=SI -show-encoding %s | FileCheck %s --check-prefix=SICI
+// RUN: llvm-mc -arch=amdgcn -mcpu=fiji -show-encoding %s | FileCheck %s --check-prefix=VI
+
+image_load v[4:6], v[237:240], s[28:35] dmask:0x7 unorm
+// SICI: image_load v[4:6], v[237:240], s[28:35] dmask:0x7 unorm ; encoding: [0x00,0x17,0x00,0xf0,0xed,0x04,0x07,0x00]
+// VI: image_load v[4:6], v[237:240], s[28:35] dmask:0x7 unorm ; encoding: [0x00,0x17,0x00,0xf0,0xed,0x04,0x07,0x00]
+
+image_store v[193:195], v[237:240], s[28:35] dmask:0x7 unorm
+// SICI: image_store v[193:195], v[237:240], s[28:35] dmask:0x7 unorm ; encoding: [0x00,0x17,0x20,0xf0,0xed,0xc1,0x07,0x00]
+// VI : image_store v[193:195], v[237:240], s[28:35] dmask:0x7 unorm ; encoding: [0x00,0x17,0x20,0xf0,0xed,0xc1,0x07,0x00]
+
+image_sample v[193:195], v[237:240], s[28:35], s[4:7] dmask:0x7 unorm
+// SICI: image_sample v[193:195], v[237:240], s[28:35], s[4:7] dmask:0x7 unorm ; encoding: [0x00,0x17,0x80,0xf0,0xed,0xc1,0x27,0x00]
+// VI : image_sample v[193:195], v[237:240], s[28:35], s[4:7] dmask:0x7 unorm ; encoding: [0x00,0x17,0x80,0xf0,0xed,0xc1,0x27,0x00]
More information about the llvm-commits
mailing list