mirror of
https://github.com/intel/compute-runtime.git
synced 2025-12-22 10:17:01 +08:00
160303924d
- For calculating number of threads per workgroup, for SIMD 1, return local work size (each software thread should be mapped into a whole hardware thread). - Correct logic of calculating space for per thread data for SIMD 1. - Minor: unit tests refactor. - Corrected naming. Related-To: NEO-8261 Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
35 lines
1.0 KiB
C++
35 lines
1.0 KiB
C++
/*
|
|
* Copyright (C) 2018-2023 Intel Corporation
|
|
*
|
|
* SPDX-License-Identifier: MIT
|
|
*
|
|
*/
|
|
|
|
#pragma once
|
|
#include "shared/source/helpers/gfx_core_helper.h"
|
|
#include "shared/source/helpers/local_id_gen.h"
|
|
#include "shared/source/helpers/simd_helper.h"
|
|
|
|
#include <cstddef>
|
|
#include <cstdint>
|
|
|
|
namespace NEO {
|
|
class LinearStream;
|
|
|
|
struct PerThreadDataHelper {
|
|
static inline size_t getPerThreadDataSizeTotal(
|
|
uint32_t simd,
|
|
uint32_t grfSize,
|
|
uint32_t numChannels,
|
|
size_t localWorkSize,
|
|
bool isHwLocalIdGeneration,
|
|
const GfxCoreHelper &gfxCoreHelper) {
|
|
auto perThreadSizeLocalIDs = static_cast<size_t>(getPerThreadSizeLocalIDs(simd, grfSize, numChannels));
|
|
if (isSimd1(simd)) {
|
|
return perThreadSizeLocalIDs * localWorkSize;
|
|
}
|
|
return perThreadSizeLocalIDs * gfxCoreHelper.calculateNumThreadsPerThreadGroup(simd, static_cast<uint32_t>(localWorkSize), grfSize, isHwLocalIdGeneration);
|
|
}
|
|
}; // namespace PerThreadDataHelper
|
|
} // namespace NEO
|