AMDGPU: Turn D16 for MIMG instructions into a regular operand
Summary:
This allows us to reduce the number of different machine instruction
opcodes, which reduces the table sizes and helps flatten the TableGen
multiclass hierarchies.
We can do this because for each hardware MIMG opcode, we have a full set
of IMAGE_xxx_Vn_Vm machine instructions for all required sizes of vdata
and vaddr registers. Instead of having separate D16 machine instructions,
a packed D16 instructions loading e.g. 4 components can simply use the
same V2 opcode variant that non-D16 instructions use.
We still require a TSFlag for D16 buffer instructions, because the
D16-ness of buffer instructions is part of the opcode. Renaming the flag
should help avoid future confusion.
The one non-obvious code change is that for gather4 instructions, the
disassembler can no longer automatically decide whether to use a V2 or
a V4 variant. The existing logic which choose the correct variant for
other MIMG instruction is extended to cover gather4 as well.
As a bonus, some of the assembler error messages are now more helpful
(e.g., complaining about a wrong data size instead of a non-existing
instruction).
While we're at it, delete a whole bunch of dead legacy TableGen code.
Change-Id: I89b02c2841c06f95e662541433e597f5d4553978
Reviewers: arsenm, rampitec, kzhuravl, artem.tamazov, dp, rtaylor
Subscribers: wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D47434
llvm-svn: 335222
diff --git a/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp b/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
index 18cc67f..57c552d 100644
--- a/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
+++ b/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
@@ -2301,10 +2301,6 @@
if ((Desc.TSFlags & SIInstrFlags::MIMG) == 0)
return true;
- // Gather4 instructions do not need validation: dst size is hardcoded.
- if (Desc.TSFlags & SIInstrFlags::Gather4)
- return true;
-
int VDataIdx = AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::vdata);
int DMaskIdx = AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::dmask);
int TFEIdx = AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::tfe);
@@ -2319,9 +2315,12 @@
if (DMask == 0)
DMask = 1;
- unsigned DataSize = countPopulation(DMask);
- if ((Desc.TSFlags & SIInstrFlags::D16) != 0 && hasPackedD16()) {
- DataSize = (DataSize + 1) / 2;
+ unsigned DataSize =
+ (Desc.TSFlags & SIInstrFlags::Gather4) ? 4 : countPopulation(DMask);
+ if (hasPackedD16()) {
+ int D16Idx = AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::d16);
+ if (D16Idx >= 0 && Inst.getOperand(D16Idx).getImm())
+ DataSize = (DataSize + 1) / 2;
}
return (VDataSize / 4) == DataSize + TFESize;
@@ -2389,10 +2388,14 @@
if ((Desc.TSFlags & SIInstrFlags::MIMG) == 0)
return true;
- if ((Desc.TSFlags & SIInstrFlags::D16) == 0)
- return true;
- return !isCI() && !isSI();
+ int D16Idx = AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::d16);
+ if (D16Idx >= 0 && Inst.getOperand(D16Idx).getImm()) {
+ if (isCI() || isSI())
+ return false;
+ }
+
+ return true;
}
bool AMDGPUAsmParser::validateInstruction(const MCInst &Inst,
@@ -4261,6 +4264,7 @@
addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyTFE);
addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyLWE);
addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyDA);
+ addOptionalImmOperand(Inst, Operands, OptionalIdx, AMDGPUOperand::ImmTyD16);
}
void AMDGPUAsmParser::cvtMIMGAtomic(MCInst &Inst, const OperandVector &Operands) {
@@ -4287,6 +4291,10 @@
return AMDGPUOperand::CreateImm(this, 0, SMLoc(), AMDGPUOperand::ImmTyLWE);
}
+AMDGPUOperand::Ptr AMDGPUAsmParser::defaultD16() const {
+ return AMDGPUOperand::CreateImm(this, 0, SMLoc(), AMDGPUOperand::ImmTyD16);
+}
+
//===----------------------------------------------------------------------===//
// smrd
//===----------------------------------------------------------------------===//
@@ -4389,6 +4397,7 @@
{"da", AMDGPUOperand::ImmTyDA, true, nullptr},
{"r128", AMDGPUOperand::ImmTyR128, true, nullptr},
{"lwe", AMDGPUOperand::ImmTyLWE, true, nullptr},
+ {"d16", AMDGPUOperand::ImmTyD16, true, nullptr},
{"dmask", AMDGPUOperand::ImmTyDMask, false, nullptr},
{"row_mask", AMDGPUOperand::ImmTyDppRowMask, false, nullptr},
{"bank_mask", AMDGPUOperand::ImmTyDppBankMask, false, nullptr},
@@ -5094,8 +5103,6 @@
return Operand.isLDS() ? Match_Success : Match_InvalidOperand;
case MCK_glc:
return Operand.isGLC() ? Match_Success : Match_InvalidOperand;
- case MCK_d16:
- return Operand.isD16() ? Match_Success : Match_InvalidOperand;
case MCK_idxen:
return Operand.isIdxen() ? Match_Success : Match_InvalidOperand;
case MCK_offen: