Function ggml_tallocr_alloc

ggml-alloc.c:82–153

}

void ggml_tallocr_alloc(ggml_tallocr_t alloc, struct ggml_tensor * tensor) {
    GGML_ASSERT(!ggml_is_view(tensor)); // views generally get data pointer from one of their sources
    GGML_ASSERT(tensor->data == NULL); // avoid allocating tensor which already has memory allocated

    size_t size = ggml_backend_buffer_get_alloc_size(alloc->buffer, tensor);
    size = aligned_offset(NULL, size, alloc->alignment);

    AT_PRINTF("%s: allocating %s (%zu bytes) - ", __func__, tensor->name, size);

    size_t max_avail = 0;

    // find the best fitting free block besides the last block
    int best_fit_block = -1;
    size_t best_fit_size = SIZE_MAX;
    for (int i = 0; i < alloc->n_free_blocks - 1; i++) {
        struct free_block * block = &alloc->free_blocks[i];
        max_avail = MAX(max_avail, block->size);
        if (block->size >= size && block->size <= best_fit_size) {
            best_fit_block = i;
            best_fit_size = block->size;
        }
    }

    AT_PRINTF("block %d\n", best_fit_block);

    if (best_fit_block == -1) {
        // the last block is our last resort
        struct free_block * block = &alloc->free_blocks[alloc->n_free_blocks - 1];
        max_avail = MAX(max_avail, block->size);
        if (block->size >= size) {
            best_fit_block = alloc->n_free_blocks - 1;
        } else {
            fprintf(stderr, "%s: not enough space in the buffer (needed %zu, largest block available %zu)\n",
                    __func__, size, max_avail);
            GGML_ASSERT(!"not enough space in the buffer");
            return;
        }
    }
    struct free_block * block = &alloc->free_blocks[best_fit_block];
    void * addr = block->addr;
    block->addr = (char*)block->addr + size;
    block->size -= size;
    if (block->size == 0) {
        // remove block if empty
        alloc->n_free_blocks--;
        for (int j = best_fit_block; j < alloc->n_free_blocks; j++) {
            alloc->free_blocks[j] = alloc->free_blocks[j+1];
        }
    }

    tensor->data = addr;
    tensor->buffer = alloc->buffer;
    if (!alloc->measure) {
        ggml_backend_buffer_init_tensor(alloc->buffer, tensor);
    }

#ifdef GGML_ALLOCATOR_DEBUG
    add_allocated_tensor(alloc, tensor);