forked from OSchip/llvm-project
[mlir][vulkan-runner] Simplify vulkan launch call op.
Summary: Workgroup size is written into the kernel. So to properly modelling vulkan launch, we have to skip local workgroup size for vulkan launch call op. Differential Revision: https://reviews.llvm.org/D78307
This commit is contained in:
Denis Khalikov
parent
ac00376a13
commit
a48f0a3c7e
|
|
@ -65,6 +65,11 @@ private:
|
|||
/// operand is unsupported by Vulkan runtime.
|
||||
LogicalResult declareVulkanLaunchFunc(Location loc,
|
||||
gpu::LaunchFuncOp launchOp);
|
||||
|
||||
private:
|
||||
/// The number of vulkan launch configuration operands, placed at the leading
|
||||
/// positions of the operand list.
|
||||
static constexpr unsigned kVulkanLaunchNumConfigOperands = 3;
|
||||
};
|
||||
|
||||
} // anonymous namespace
|
||||
|
|
@ -93,14 +98,23 @@ void ConvertGpuLaunchFuncToVulkanLaunchFunc::runOnOperation() {
|
|||
LogicalResult ConvertGpuLaunchFuncToVulkanLaunchFunc::declareVulkanLaunchFunc(
|
||||
Location loc, gpu::LaunchFuncOp launchOp) {
|
||||
OpBuilder builder(getOperation().getBody()->getTerminator());
|
||||
// TODO: Workgroup size is written into the kernel. So to properly modelling
|
||||
// vulkan launch, we cannot have the local workgroup size configuration here.
|
||||
SmallVector<Type, 8> vulkanLaunchTypes{launchOp.getOperandTypes()};
|
||||
|
||||
// Check that all operands have supported types except those for the launch
|
||||
// configuration.
|
||||
// Workgroup size is written into the kernel. So to properly modelling
|
||||
// vulkan launch, we have to skip local workgroup size configuration here.
|
||||
SmallVector<Type, 8> gpuLaunchTypes(launchOp.getOperandTypes());
|
||||
// The first kVulkanLaunchNumConfigOperands of the gpu.launch_func op are the
|
||||
// same as the config operands for the vulkan launch call op.
|
||||
SmallVector<Type, 8> vulkanLaunchTypes(gpuLaunchTypes.begin(),
|
||||
gpuLaunchTypes.begin() +
|
||||
kVulkanLaunchNumConfigOperands);
|
||||
vulkanLaunchTypes.append(gpuLaunchTypes.begin() +
|
||||
gpu::LaunchOp::kNumConfigOperands,
|
||||
gpuLaunchTypes.end());
|
||||
|
||||
// Check that all operands have supported types except those for the
|
||||
// launch configuration.
|
||||
for (auto type :
|
||||
llvm::drop_begin(vulkanLaunchTypes, gpu::LaunchOp::kNumConfigOperands)) {
|
||||
llvm::drop_begin(vulkanLaunchTypes, kVulkanLaunchNumConfigOperands)) {
|
||||
if (!isSupportedType(type))
|
||||
return launchOp.emitError() << type << " is unsupported to run on Vulkan";
|
||||
}
|
||||
|
|
@ -147,10 +161,18 @@ void ConvertGpuLaunchFuncToVulkanLaunchFunc::convertGpuLaunchFunc(
|
|||
if (failed(declareVulkanLaunchFunc(loc, launchOp)))
|
||||
return signalPassFailure();
|
||||
|
||||
SmallVector<Value, 8> gpuLaunchOperands(launchOp.getOperands());
|
||||
SmallVector<Value, 8> vulkanLaunchOperands(
|
||||
gpuLaunchOperands.begin(),
|
||||
gpuLaunchOperands.begin() + kVulkanLaunchNumConfigOperands);
|
||||
vulkanLaunchOperands.append(gpuLaunchOperands.begin() +
|
||||
gpu::LaunchOp::kNumConfigOperands,
|
||||
gpuLaunchOperands.end());
|
||||
|
||||
// Create vulkan launch call op.
|
||||
auto vulkanLaunchCallOp = builder.create<CallOp>(
|
||||
loc, ArrayRef<Type>{}, builder.getSymbolRefAttr(kVulkanLaunch),
|
||||
launchOp.getOperands());
|
||||
vulkanLaunchOperands);
|
||||
|
||||
// Set SPIR-V binary shader data as an attribute.
|
||||
vulkanLaunchCallOp.setAttr(
|
||||
|
|
|
|||
|
|
@ -16,7 +16,6 @@
|
|||
|
||||
#include "../PassDetail.h"
|
||||
#include "mlir/Conversion/GPUToVulkan/ConvertGPUToVulkanPass.h"
|
||||
#include "mlir/Dialect/GPU/GPUDialect.h"
|
||||
#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
|
||||
#include "mlir/IR/Attributes.h"
|
||||
#include "mlir/IR/Builders.h"
|
||||
|
|
@ -121,7 +120,7 @@ private:
|
|||
/// Checks whether the given LLVM::CallOp is a vulkan launch call op.
|
||||
bool isVulkanLaunchCallOp(LLVM::CallOp callOp) {
|
||||
return (callOp.callee() && callOp.callee().getValue() == kVulkanLaunch &&
|
||||
callOp.getNumOperands() >= gpu::LaunchOp::kNumConfigOperands);
|
||||
callOp.getNumOperands() >= kVulkanLaunchNumConfigOperands);
|
||||
}
|
||||
|
||||
/// Checks whether the given LLVM::CallOp is a "ci_face" vulkan launch call
|
||||
|
|
@ -129,7 +128,7 @@ private:
|
|||
bool isCInterfaceVulkanLaunchCallOp(LLVM::CallOp callOp) {
|
||||
return (callOp.callee() &&
|
||||
callOp.callee().getValue() == kCInterfaceVulkanLaunch &&
|
||||
callOp.getNumOperands() >= gpu::LaunchOp::kNumConfigOperands);
|
||||
callOp.getNumOperands() >= kVulkanLaunchNumConfigOperands);
|
||||
}
|
||||
|
||||
/// Translates the given `vulkanLaunchCallOp` to the sequence of Vulkan
|
||||
|
|
@ -162,6 +161,9 @@ private:
|
|||
|
||||
// TODO: Use an associative array to support multiple vulkan launch calls.
|
||||
std::pair<StringAttr, StringAttr> spirvAttributes;
|
||||
/// The number of vulkan launch configuration operands, placed at the leading
|
||||
/// positions of the operand list.
|
||||
static constexpr unsigned kVulkanLaunchNumConfigOperands = 3;
|
||||
};
|
||||
|
||||
} // anonymous namespace
|
||||
|
|
@ -209,7 +211,7 @@ void VulkanLaunchFuncToVulkanCallsPass::collectSPIRVAttributes(
|
|||
void VulkanLaunchFuncToVulkanCallsPass::createBindMemRefCalls(
|
||||
LLVM::CallOp cInterfaceVulkanLaunchCallOp, Value vulkanRuntime) {
|
||||
if (cInterfaceVulkanLaunchCallOp.getNumOperands() ==
|
||||
gpu::LaunchOp::kNumConfigOperands)
|
||||
kVulkanLaunchNumConfigOperands)
|
||||
return;
|
||||
OpBuilder builder(cInterfaceVulkanLaunchCallOp);
|
||||
Location loc = cInterfaceVulkanLaunchCallOp.getLoc();
|
||||
|
|
@ -222,7 +224,7 @@ void VulkanLaunchFuncToVulkanCallsPass::createBindMemRefCalls(
|
|||
|
||||
for (auto en :
|
||||
llvm::enumerate(cInterfaceVulkanLaunchCallOp.getOperands().drop_front(
|
||||
gpu::LaunchOp::kNumConfigOperands))) {
|
||||
kVulkanLaunchNumConfigOperands))) {
|
||||
// Create LLVM constant for the descriptor binding index.
|
||||
Value descriptorBinding = builder.create<LLVM::ConstantOp>(
|
||||
loc, getInt32Type(), builder.getI32IntegerAttr(en.index()));
|
||||
|
|
|
|||
|
|
@ -40,11 +40,11 @@ module attributes {gpu.container_module} {
|
|||
%19 = llvm.extractvalue %15[2] : !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }">
|
||||
%20 = llvm.extractvalue %15[3, 0] : !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }">
|
||||
%21 = llvm.extractvalue %15[4, 0] : !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }">
|
||||
llvm.call @vulkanLaunch(%16, %16, %16, %16, %16, %16, %17, %18, %19, %20, %21) {spirv_blob = "\03\02#\07\00", spirv_entry_point = "kernel"}
|
||||
: (!llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm<"float*">, !llvm<"float*">, !llvm.i64, !llvm.i64, !llvm.i64) -> ()
|
||||
llvm.call @vulkanLaunch(%16, %16, %16, %17, %18, %19, %20, %21) {spirv_blob = "\03\02#\07\00", spirv_entry_point = "kernel"}
|
||||
: (!llvm.i64, !llvm.i64, !llvm.i64, !llvm<"float*">, !llvm<"float*">, !llvm.i64, !llvm.i64, !llvm.i64) -> ()
|
||||
llvm.return
|
||||
}
|
||||
llvm.func @vulkanLaunch(%arg0: !llvm.i64, %arg1: !llvm.i64, %arg2: !llvm.i64, %arg3: !llvm.i64, %arg4: !llvm.i64, %arg5: !llvm.i64, %arg6: !llvm<"float*">, %arg7: !llvm<"float*">, %arg8: !llvm.i64, %arg9: !llvm.i64, %arg10: !llvm.i64) {
|
||||
llvm.func @vulkanLaunch(%arg0: !llvm.i64, %arg1: !llvm.i64, %arg2: !llvm.i64, %arg6: !llvm<"float*">, %arg7: !llvm<"float*">, %arg8: !llvm.i64, %arg9: !llvm.i64, %arg10: !llvm.i64) {
|
||||
%0 = llvm.mlir.undef : !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }">
|
||||
%1 = llvm.insertvalue %arg6, %0[0] : !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }">
|
||||
%2 = llvm.insertvalue %arg7, %1[1] : !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }">
|
||||
|
|
@ -54,8 +54,8 @@ module attributes {gpu.container_module} {
|
|||
%6 = llvm.mlir.constant(1 : index) : !llvm.i64
|
||||
%7 = llvm.alloca %6 x !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }"> : (!llvm.i64) -> !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }*">
|
||||
llvm.store %5, %7 : !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }*">
|
||||
llvm.call @_mlir_ciface_vulkanLaunch(%arg0, %arg1, %arg2, %arg3, %arg4, %arg5, %7) : (!llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }*">) -> ()
|
||||
llvm.call @_mlir_ciface_vulkanLaunch(%arg0, %arg1, %arg2, %7) : (!llvm.i64, !llvm.i64, !llvm.i64, !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }*">) -> ()
|
||||
llvm.return
|
||||
}
|
||||
llvm.func @_mlir_ciface_vulkanLaunch(!llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm.i64, !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }*">)
|
||||
llvm.func @_mlir_ciface_vulkanLaunch(!llvm.i64, !llvm.i64, !llvm.i64, !llvm<"{ float*, float*, i64, [1 x i64], [1 x i64] }*">)
|
||||
}
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
// CHECK: %[[resource:.*]] = alloc() : memref<12xf32>
|
||||
// CHECK: %[[index:.*]] = constant 1 : index
|
||||
// CHECK: call @vulkanLaunch(%[[index]], %[[index]], %[[index]], %[[index]], %[[index]], %[[index]], %[[resource]]) {spirv_blob = "{{.*}}", spirv_entry_point = "kernel"}
|
||||
// CHECK: call @vulkanLaunch(%[[index]], %[[index]], %[[index]], %[[resource]]) {spirv_blob = "{{.*}}", spirv_entry_point = "kernel"}
|
||||
|
||||
module attributes {gpu.container_module} {
|
||||
spv.module Logical GLSL450 requires #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]> {
|
||||
|
|
|
|||
Loading…
Reference in New Issue