mirror of
https://github.com/blender/blender
synced 2026-09-29 04:37:17 +03:00
0230a528f8
Initially, KIP-RT module essentially included all kernels, not only the ones that do intersection checks. This changes makes it so the HIP-RT module only includes kernels that use intersections checks, making it behave closer to how CUDA and OptiX modules are structured. There does not seem to be direct impact on the performance, but perhaps it could still help compiler to avoid making bad decisions. It does help with the compilation: building the HIP-RT kernel for gfx1201 goes down from 1min 47sec to 58sec on the test machine (i5-8600K). The uncompressed kernel_rt_gfx1201.hipfb goes down from 6.5Mb to 3.2Mb, and compressed size goes down from 1Mb to 790Kb. The HIP-RT's kernel.cpp is now structured closer to how gpu/kernel.h is structured, potentially making it easier to move the signatures to the common place. There is also potential to split shader ray-trace kernel to separate module, following OptiX for potentially better performance as well. However, from quick tests that does not give any immediate speedup measured when removing shade raytrace code from the module. Pull Request: https://projects.blender.org/blender/blender/pulls/152081
45 lines
946 B
C++
45 lines
946 B
C++
/* SPDX-FileCopyrightText: 2011-2022 Blender Foundation
|
|
*
|
|
* SPDX-License-Identifier: Apache-2.0 */
|
|
|
|
#pragma once
|
|
|
|
#ifdef WITH_HIP
|
|
|
|
# include "device/kernel.h"
|
|
|
|
# ifdef WITH_HIP_DYNLOAD
|
|
# include "hipew.h"
|
|
# endif
|
|
|
|
CCL_NAMESPACE_BEGIN
|
|
|
|
class HIPDevice;
|
|
|
|
/* HIP kernel and associate occupancy information. */
|
|
class HIPDeviceKernel {
|
|
public:
|
|
hipFunction_t function = nullptr;
|
|
|
|
int num_threads_per_block = 0;
|
|
int min_blocks = 0;
|
|
};
|
|
|
|
/* Cache of HIP kernels for each DeviceKernel. */
|
|
class HIPDeviceKernels {
|
|
public:
|
|
void load_all(HIPDevice *device, hipModule_t hip_module);
|
|
void load_raytrace(HIPDevice *device, hipModule_t hip_module);
|
|
|
|
const HIPDeviceKernel &get(DeviceKernel kernel) const;
|
|
bool available(DeviceKernel kernel) const;
|
|
|
|
protected:
|
|
bool load_kernel(HIPDevice *device, hipModule_t hip_module, DeviceKernel kernel);
|
|
|
|
HIPDeviceKernel kernels_[DEVICE_KERNEL_NUM];
|
|
};
|
|
|
|
CCL_NAMESPACE_END
|
|
|
|
#endif /* WITH_HIP */
|