Function ggml_tallocr_free_tensor

ggml-alloc.c:156–225

this is a very naive implementation, but for our case the number of free blocks should be very small

// this is a very naive implementation, but for our case the number of free blocks should be very small
static void ggml_tallocr_free_tensor(ggml_tallocr_t alloc, struct ggml_tensor * tensor) {
    if (ggml_tallocr_is_own(alloc, tensor) == false) {
        // the tensor was not allocated in this buffer
        // this can happen because the graph allocator will try to free weights and other tensors from different buffers
        // the easiest way to deal with this is just to ignore it
        // AT_PRINTF("ignoring %s (their buffer: %p, our buffer: %p)\n", tensor->name, (void *)tensor->buffer, (void *)alloc->buffer);
        return;
    }

    void * ptr = tensor->data;

    size_t size = ggml_backend_buffer_get_alloc_size(alloc->buffer, tensor);
    size = aligned_offset(NULL, size, alloc->alignment);
    AT_PRINTF("%s: freeing %s at %p (%zu bytes) - n_free_blocks = %d\n", __func__, tensor->name, ptr, size, alloc->n_free_blocks);

    if (!alloc->measure) {
        ggml_backend_buffer_free_tensor(alloc->buffer, tensor);
    }

#ifdef GGML_ALLOCATOR_DEBUG
    remove_allocated_tensor(alloc, tensor);
#endif

    // see if we can merge with an existing block
    for (int i = 0; i < alloc->n_free_blocks; i++) {
        struct free_block * block = &alloc->free_blocks[i];
        // check if ptr is at the end of the block
        if ((char*)block->addr + block->size == ptr) {
            block->size += size;
            // check if we can merge with the next block
            if (i < alloc->n_free_blocks - 1 && (char*)block->addr + block->size == alloc->free_blocks[i+1].addr) {
                block->size += alloc->free_blocks[i+1].size;
                alloc->n_free_blocks--;
                for (int j = i+1; j < alloc->n_free_blocks; j++) {
                    alloc->free_blocks[j] = alloc->free_blocks[j+1];
                }
            }
            return;
        }
        // check if ptr is at the beginning of the block
        if ((char*)ptr + size == block->addr) {
            block->addr = ptr;
            block->size += size;
            // check if we can merge with the previous block
            if (i > 0 && (char*)alloc->free_blocks[i-1].addr + alloc->free_blocks[i-1].size == block->addr) {
                alloc->free_blocks[i-1].size += block->size;
                alloc->n_free_blocks--;
                for (int j = i; j < alloc->n_free_blocks; j++) {
                    alloc->free_blocks[j] = alloc->free_blocks[j+1];
                }
            }
            return;
        }
    }
    // otherwise, add a new block
    GGML_ASSERT(alloc->n_free_blocks < MAX_FREE_BLOCKS && "out of free blocks");
    // insert the new block in the correct position to keep the array sorted by address (to make merging blocks faster)
    int insert_pos = 0;