Skip to content

fix: use vm_allocate instead of posix_memalign for Metal on macOS #7078

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 5 commits into from
May 8, 2024
Merged

fix: use vm_allocate instead of posix_memalign for Metal on macOS #7078

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
571dca5
fix: use `malloc` instead of `posix_memalign` in `ggml-metal.m` to ma…
giladgd May 4, 2024
a53e517
fix: typo
giladgd May 4, 2024
bfa4dae
fix: use `vm_allocate` instead of `posix_memalign`
giladgd May 4, 2024
a92efec
fix: don't call `newBufferWithBytesNoCopy` with `NULL` when `ggml_met…
giladgd May 4, 2024
78214ac
fix: use `vm_allocate` only on macOS
giladgd May 4, 2024
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
29 changes: 22 additions & 7 deletions ggml-metal.m
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -265,11 +265,20 @@ static void ggml_metal_log(enum ggml_log_level level, const char * format, ...){

static void * ggml_metal_host_malloc(size_t n) {
void * data = NULL;

#if TARGET_OS_OSX
kern_return_t err = vm_allocate((vm_map_t) mach_task_self(), (void *) &data, n, VM_FLAGS_ANYWHERE);
if (err != KERN_SUCCESS) {
GGML_METAL_LOG_ERROR("%s: error: vm_allocate failed\n", __func__);
return NULL;
}
#else
const int result = posix_memalign((void **) &data, sysconf(_SC_PAGESIZE), n);
if (result != 0) {
GGML_METAL_LOG_ERROR("%s: error: posix_memalign failed\n", __func__);
return NULL;
}
#endif

return data;
}
Expand Down Expand Up @@ -2840,7 +2849,11 @@ GGML_CALL static void ggml_backend_metal_buffer_free_buffer(ggml_backend_buffer_
ggml_backend_metal_free_device();

if (ctx->owned) {
#if TARGET_OS_OSX
vm_deallocate((vm_map_t)mach_task_self(), (vm_address_t)ctx->all_data, ctx->all_size);
#else
free(ctx->all_data);
#endif
}

free(ctx);
Expand Down Expand Up @@ -2944,14 +2957,16 @@ GGML_CALL static ggml_backend_buffer_t ggml_backend_metal_buffer_type_alloc_buff
ctx->owned = true;
ctx->n_buffers = 1;

ctx->buffers[0].data = ctx->all_data;
ctx->buffers[0].size = size;
ctx->buffers[0].metal = [device newBufferWithBytesNoCopy:ctx->all_data
length:size_aligned
options:MTLResourceStorageModeShared
deallocator:nil];
if (ctx->all_data != NULL) {
ctx->buffers[0].data = ctx->all_data;
ctx->buffers[0].size = size;
ctx->buffers[0].metal = [device newBufferWithBytesNoCopy:ctx->all_data
length:size_aligned
options:MTLResourceStorageModeShared
deallocator:nil];
}

if (ctx->buffers[0].metal == nil) {
if (ctx->all_data == NULL || ctx->buffers[0].metal == nil) {
GGML_METAL_LOG_ERROR("%s: error: failed to allocate buffer, size = %8.2f MiB\n", __func__, size_aligned / 1024.0 / 1024.0);
free(ctx);
ggml_backend_metal_free_device();
Expand Down