Skip to content

Enable use to the rebar feature to upload buffers to the device. #9251

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 28, 2024
Merged

Enable use to the rebar feature to upload buffers to the device. #9251

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions ggml/src/ggml-vulkan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1076,7 +1076,8 @@ static vk_buffer ggml_vk_create_buffer_device(vk_device& device, size_t size) {
// Fall back to host memory type
buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eDeviceLocal, vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent);
} else {
buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eDeviceLocal);
// use rebar if available, otherwise fallback to device only visible memory
buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eDeviceLocal | vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent, vk::MemoryPropertyFlagBits::eDeviceLocal);
}
} catch (const vk::SystemError& e) {
std::cerr << "ggml_vulkan: Device memory allocation of size " << size << " failed." << std::endl;
Expand Down Expand Up @@ -2803,7 +2804,11 @@ static void ggml_vk_buffer_read_async(vk_context subctx, vk_buffer& src, size_t

static void ggml_vk_buffer_read(vk_buffer& src, size_t offset, void * dst, size_t size) {
VK_LOG_DEBUG("ggml_vk_buffer_read(" << src->buffer << ", " << offset << ", " << size << ")");
if(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible) {

// If the device is not an UMA device the memory is host-accessible through rebar. While writing
// through PCIe is sufficient fast reading back data from PCIe is slower than going through
// the HW device to host copy path.
if(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible && src->device->uma) {
GGML_ASSERT(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostCoherent);

memcpy(dst, (uint8_t *) src->ptr + offset, size);
Expand Down
Loading