1b0ddfa6cb
PR Introduces GPU_storagebuf_sync_to_host as an explicit routine to flush GPU-resident storage buffer memory back to the host within the GPU command stream. The previous implmentation relied on implicit synchronization of resources using OpenGL barriers which does not match the paradigm of explicit APIs, where indiviaul resources may need to be tracked. This patch ensures GPU_storagebuf_read can be called without stalling the GPU pipeline while work finishes executing. There are two possible use cases: 1) If GPU_storagebuf_read is called AFTER an explicit call to GPU_storagebuf_sync_to_host, the read will be synchronized. If the dependent work is still executing on the GPU, the host will stall until GPU work has completed and results are available. 2) If GPU_storagebuf_read is called WITHOUT an explicit call to GPU_storagebuf_sync_to_host, the read will be asynchronous and whatever memory is visible to the host at that time will be used. (This is the same as assuming a sync event has already been signalled.) This patch also addresses a gap in the Metal implementation where there was missing read support for GPU-only storage buffers. This routine now uses a staging buffer to copy results if no host-visible buffer was available. Reading from a GPU-only storage buffer will always stall the host, as it is not possible to pre-flush results, as no host-resident buffer is available. Authored by Apple: Michael Parkin-White Pull Request: https://projects.blender.org/blender/blender/pulls/113456
71 lines
1.6 KiB
C++
71 lines
1.6 KiB
C++
/* SPDX-FileCopyrightText: 2022 Blender Authors
|
|
*
|
|
* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
|
|
/** \file
|
|
* \ingroup gpu
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "BLI_span.hh"
|
|
#include "BLI_sys_types.h"
|
|
|
|
struct GPUStorageBuf;
|
|
|
|
namespace blender {
|
|
namespace gpu {
|
|
|
|
class VertBuf;
|
|
|
|
#ifdef DEBUG
|
|
# define DEBUG_NAME_LEN 64
|
|
#else
|
|
# define DEBUG_NAME_LEN 8
|
|
#endif
|
|
|
|
/**
|
|
* Implementation of Storage Buffers.
|
|
* Base class which is then specialized for each implementation (GL, VK, ...).
|
|
*/
|
|
class StorageBuf {
|
|
protected:
|
|
/** Data size in bytes. */
|
|
size_t size_in_bytes_;
|
|
/** Continuous memory block to copy to GPU. This data is owned by the StorageBuf. */
|
|
void *data_ = nullptr;
|
|
/** Debugging name */
|
|
char name_[DEBUG_NAME_LEN];
|
|
|
|
public:
|
|
StorageBuf(size_t size, const char *name);
|
|
virtual ~StorageBuf();
|
|
|
|
virtual void update(const void *data) = 0;
|
|
virtual void bind(int slot) = 0;
|
|
virtual void unbind() = 0;
|
|
virtual void clear(uint32_t clear_value) = 0;
|
|
virtual void copy_sub(VertBuf *src, uint dst_offset, uint src_offset, uint copy_size) = 0;
|
|
virtual void read(void *data) = 0;
|
|
virtual void async_flush_to_host() = 0;
|
|
};
|
|
|
|
/* Syntactic sugar. */
|
|
static inline GPUStorageBuf *wrap(StorageBuf *storage_buf)
|
|
{
|
|
return reinterpret_cast<GPUStorageBuf *>(storage_buf);
|
|
}
|
|
static inline StorageBuf *unwrap(GPUStorageBuf *storage_buf)
|
|
{
|
|
return reinterpret_cast<StorageBuf *>(storage_buf);
|
|
}
|
|
static inline const StorageBuf *unwrap(const GPUStorageBuf *storage_buf)
|
|
{
|
|
return reinterpret_cast<const StorageBuf *>(storage_buf);
|
|
}
|
|
|
|
#undef DEBUG_NAME_LEN
|
|
|
|
} // namespace gpu
|
|
} // namespace blender
|