forked from OSchip/llvm-project
[mlir][gpu] Refactor functions for workgroup and private buffer attributions.
Summary: Consolidate interfaces adding workgroup and private buffer attributions in GPU dialect. Note all private buffer attributions must follow workgroup buffer attributions. Reviewers: herhut Subscribers: mehdi_amini, rriddle, jpienaar, shauheen, antiagainst, nicolasvasilache, csigg, arpith-jacob, mgester, lucyrfox, liufengdb, stephenneuendorffer, Joonsoo, grosul1, frgossen, Kayjukh, llvm-commits Tags: #llvm, #mlir Differential Revision: https://reviews.llvm.org/D79508
This commit is contained in:
parent
cdb6f05e2d
commit
ad398164ba
|
@ -161,10 +161,6 @@ def GPU_GPUFuncOp : GPU_Op<"func", [HasParent<"GPUModuleOp">,
|
|||
];
|
||||
|
||||
let extraClassDeclaration = [{
|
||||
/// Adds a workgroup attribution of the MemRef type with the given shape and
|
||||
/// element type.
|
||||
Value addWorkgroupAttribution(ArrayRef<int64_t> shape, Type elementType);
|
||||
|
||||
/// Returns `true` if the GPU function defined by this Op is a kernel, i.e.
|
||||
/// it is intended to be launched from host.
|
||||
bool isKernel() {
|
||||
|
@ -198,25 +194,31 @@ def GPU_GPUFuncOp : GPU_Op<"func", [HasParent<"GPUModuleOp">,
|
|||
return {begin, end};
|
||||
}
|
||||
|
||||
// Adds a new block argument that corresponds to buffers located in
|
||||
// workgroup memory.
|
||||
BlockArgument addWorkgroupAttribution(Type type) {
|
||||
auto attrName = getNumWorkgroupAttributionsAttrName();
|
||||
auto attr = getAttrOfType<IntegerAttr>(attrName);
|
||||
setAttr(attrName, IntegerAttr::get(attr.getType(), attr.getValue() + 1));
|
||||
return getBody().front().insertArgument(
|
||||
getType().getNumInputs() + attr.getInt(), type);
|
||||
/// Adds a new block argument that corresponds to buffers located in
|
||||
/// workgroup memory.
|
||||
BlockArgument addWorkgroupAttribution(Type type);
|
||||
|
||||
/// Returns the number of buffers located in the private memory.
|
||||
unsigned getNumPrivateAttributions() {
|
||||
return getOperation()->getNumOperands() - getType().getNumInputs() -
|
||||
getNumWorkgroupAttributions();
|
||||
}
|
||||
|
||||
/// Returns a list of block arguments that correspond to buffers located in
|
||||
/// the private memory.
|
||||
ArrayRef<BlockArgument> getPrivateAttributions() {
|
||||
// Buffers on the private memory always come after buffers on the workgroup
|
||||
// memory.
|
||||
auto begin =
|
||||
std::next(getBody().front().args_begin(),
|
||||
getType().getNumInputs() + getNumWorkgroupAttributions());
|
||||
return {begin, getBody().front().args_end()};
|
||||
}
|
||||
|
||||
/// Adds a new block argument that corresponds to buffers located in
|
||||
/// private memory.
|
||||
BlockArgument addPrivateAttribution(Type type);
|
||||
|
||||
/// Returns the name of the attribute containing the number of buffers
|
||||
/// located in the workgroup memory.
|
||||
static StringRef getNumWorkgroupAttributionsAttrName() {
|
||||
|
|
|
@ -457,22 +457,22 @@ static LogicalResult verify(LaunchFuncOp op) {
|
|||
// GPUFuncOp
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
/// Adds a workgroup attribution to "op" of the MemRef type with the given shape
|
||||
/// and element type.
|
||||
Value GPUFuncOp::addWorkgroupAttribution(ArrayRef<int64_t> shape,
|
||||
Type elementType) {
|
||||
unsigned pos = getNumFuncArguments() + getNumWorkgroupAttributions();
|
||||
Block &bodyBlock = body().front();
|
||||
Value attribution = bodyBlock.insertArgument(
|
||||
std::next(bodyBlock.args_begin(), pos),
|
||||
MemRefType::get(shape, elementType, /*affineMapComposition=*/{},
|
||||
GPUDialect::getWorkgroupAddressSpace()));
|
||||
auto numWorkgroupBuffersAttr =
|
||||
getAttrOfType<IntegerAttr>(getNumWorkgroupAttributionsAttrName());
|
||||
setAttr(getNumWorkgroupAttributionsAttrName(),
|
||||
IntegerAttr::get(numWorkgroupBuffersAttr.getType(),
|
||||
numWorkgroupBuffersAttr.getValue() + 1));
|
||||
return attribution;
|
||||
/// Adds a new block argument that corresponds to buffers located in
|
||||
/// workgroup memory.
|
||||
BlockArgument GPUFuncOp::addWorkgroupAttribution(Type type) {
|
||||
auto attrName = getNumWorkgroupAttributionsAttrName();
|
||||
auto attr = getAttrOfType<IntegerAttr>(attrName);
|
||||
setAttr(attrName, IntegerAttr::get(attr.getType(), attr.getValue() + 1));
|
||||
return getBody().front().insertArgument(
|
||||
getType().getNumInputs() + attr.getInt(), type);
|
||||
}
|
||||
|
||||
/// Adds a new block argument that corresponds to buffers located in
|
||||
/// private memory.
|
||||
BlockArgument GPUFuncOp::addPrivateAttribution(Type type) {
|
||||
// Buffers on the private memory always come after buffers on the workgroup
|
||||
// memory.
|
||||
return getBody().front().addArgument(type);
|
||||
}
|
||||
|
||||
void GPUFuncOp::build(OpBuilder &builder, OperationState &result,
|
||||
|
@ -675,10 +675,13 @@ static LogicalResult verifyAttributions(Operation *op,
|
|||
LogicalResult GPUFuncOp::verifyBody() {
|
||||
unsigned numFuncArguments = getNumArguments();
|
||||
unsigned numWorkgroupAttributions = getNumWorkgroupAttributions();
|
||||
unsigned numPrivateAttributions = getNumPrivateAttributions();
|
||||
unsigned numBlockArguments = front().getNumArguments();
|
||||
if (numBlockArguments < numFuncArguments + numWorkgroupAttributions)
|
||||
if (numBlockArguments <
|
||||
numFuncArguments + numWorkgroupAttributions + numPrivateAttributions)
|
||||
return emitOpError() << "expected at least "
|
||||
<< numFuncArguments + numWorkgroupAttributions
|
||||
<< numFuncArguments + numWorkgroupAttributions +
|
||||
numPrivateAttributions
|
||||
<< " arguments to body region";
|
||||
|
||||
ArrayRef<Type> funcArgTypes = getType().getInputs();
|
||||
|
|
|
@ -151,7 +151,8 @@ private:
|
|||
|
||||
/// Adds type to funcOp's workgroup attributions.
|
||||
Value createWorkgroupBuffer() {
|
||||
int workgroupMemoryAddressSpace = 3;
|
||||
int workgroupMemoryAddressSpace =
|
||||
gpu::GPUDialect::getWorkgroupAddressSpace();
|
||||
auto bufferType =
|
||||
MemRefType::get({kSubgroupSize}, valueType, ArrayRef<AffineMap>{},
|
||||
workgroupMemoryAddressSpace);
|
||||
|
|
|
@ -162,8 +162,12 @@ void mlir::promoteToWorkgroupMemory(GPUFuncOp op, unsigned arg) {
|
|||
auto type = value.getType().dyn_cast<MemRefType>();
|
||||
assert(type && type.hasStaticShape() && "can only promote memrefs");
|
||||
|
||||
Value attribution =
|
||||
op.addWorkgroupAttribution(type.getShape(), type.getElementType());
|
||||
// Get the type of the buffer in the workgroup memory.
|
||||
int workgroupMemoryAddressSpace = gpu::GPUDialect::getWorkgroupAddressSpace();
|
||||
auto bufferType = MemRefType::get(type.getShape(), type.getElementType(), {},
|
||||
workgroupMemoryAddressSpace);
|
||||
|
||||
Value attribution = op.addWorkgroupAttribution(bufferType);
|
||||
|
||||
// Replace the uses first since only the original uses are currently present.
|
||||
// Then insert the copies.
|
||||
|
|
Loading…
Reference in New Issue