vulkan: split buffers and debug code into separate files, add shared headers

ggml/src/ggml-vulkan/CMakeLists.txt

@@ -62,6 +62,11 @@ if (Vulkan_FOUND)
     ggml_add_backend_library(ggml-vulkan
                              ggml-vulkan.cpp
                              ../../include/ggml-vulkan.h
+                             ggml-vulkan-types.h
+                             ggml-vulkan-push-constants.h
+                             ggml-vulkan-common.h
+                             ggml-vulkan-buffers.cpp
+                             ggml-vulkan-debug.cpp
                             )
 
     set(VULKAN_SHADER_GEN_CMAKE_ARGS "")

ggml/src/ggml-vulkan/ggml-vulkan-buffers.cpp

@@ -0,0 +1,783 @@
+#include "ggml-vulkan-common.h"
+
+ggml_backend_buffer_type_i ggml_backend_vk_buffer_type_interface = {
+    /* .get_name         = */ ggml_backend_vk_buffer_type_name,
+    /* .alloc_buffer     = */ ggml_backend_vk_buffer_type_alloc_buffer,
+    /* .get_alignment    = */ ggml_backend_vk_buffer_type_get_alignment,
+    /* .get_max_size     = */ ggml_backend_vk_buffer_type_get_max_size,
+    /* .get_alloc_size   = */ ggml_backend_vk_buffer_type_get_alloc_size,
+    /* .is_host          = */ NULL,
+};
+
+static std::vector<uint32_t> ggml_vk_find_memory_properties(const vk::PhysicalDeviceMemoryProperties* mem_props, vk::MemoryRequirements* mem_req, vk::MemoryPropertyFlags flags) {
+    std::vector<uint32_t> indices;
+
+    for (uint32_t i = 0; i < mem_props->memoryTypeCount; ++i) {
+        vk::MemoryType memory_type = mem_props->memoryTypes[i];
+        if ((mem_req->memoryTypeBits & ((uint64_t)1 << i)) &&
+            (flags & memory_type.propertyFlags) == flags &&
+            mem_props->memoryHeaps[memory_type.heapIndex].size >= mem_req->size) {
+            indices.push_back(i);
+        }
+    }
+    return indices;
+}
+
+static vk_buffer ggml_vk_create_buffer(vk_device& device, size_t size, const std::initializer_list<vk::MemoryPropertyFlags> & req_flags_list,
+                                       void *import_ptr = nullptr) {
+    VK_LOG_DEBUG("ggml_vk_create_buffer(" << device->name << ", " << size << ", " << to_string(req_flags_list.begin()[0]) << ", " << to_string(req_flags_list.begin()[req_flags_list.size()-1]) << ")");
+    if (size > device->max_buffer_size) {
+        throw vk::OutOfDeviceMemoryError("Requested buffer size exceeds device buffer size limit");
+    }
+
+    vk_buffer buf = std::make_shared<vk_buffer_struct>();
+
+    if (size == 0) {
+        buf->size = 0;
+        return buf;
+    }
+
+    vk::BufferUsageFlags usage_flags = vk::BufferUsageFlagBits::eStorageBuffer | vk::BufferUsageFlagBits::eTransferSrc | vk::BufferUsageFlagBits::eTransferDst;
+    vk::MemoryAllocateFlags mem_flags {};
+    if (device->buffer_device_address) {
+        usage_flags |= vk::BufferUsageFlagBits::eShaderDeviceAddress;
+        mem_flags |= vk::MemoryAllocateFlagBits::eDeviceAddress;
+    }
+
+    vk::BufferCreateInfo buffer_create_info{
+        vk::BufferCreateFlags(),
+        size,
+        usage_flags,
+        vk::SharingMode::eExclusive,
+        0,
+        nullptr,
+    };
+
+    vk::ExternalMemoryBufferCreateInfo external_memory_bci;
+    if (import_ptr) {
+        external_memory_bci.handleTypes = vk::ExternalMemoryHandleTypeFlagBits::eHostAllocationEXT;
+        buffer_create_info.setPNext(&external_memory_bci);
+    }
+
+    buf->buffer = device->device.createBuffer(buffer_create_info);
+
+    vk::MemoryRequirements mem_req = device->device.getBufferMemoryRequirements(buf->buffer);
+
+    vk::PhysicalDeviceMemoryProperties mem_props = device->physical_device.getMemoryProperties();
+
+    const vk::MemoryPriorityAllocateInfoEXT mem_priority_info { 1.0f };
+
+    vk::MemoryAllocateFlagsInfo mem_flags_info { mem_flags };
+
+    if (device->memory_priority) {
+        mem_flags_info.setPNext(&mem_priority_info);
+    }
+
+    if (import_ptr) {
+        vk::MemoryHostPointerPropertiesEXT host_pointer_props;
+        try {
+            host_pointer_props = device->device.getMemoryHostPointerPropertiesEXT(vk::ExternalMemoryHandleTypeFlagBits::eHostAllocationEXT, import_ptr);
+        } catch (vk::SystemError& e) {
+            GGML_LOG_WARN("ggml_vulkan: Failed getMemoryHostPointerPropertiesEXT (%s)\n", e.what());
+            device->device.destroyBuffer(buf->buffer);
+            return {};
+        }
+        vk::PhysicalDeviceMemoryProperties mem_props = device->physical_device.getMemoryProperties();
+
+        uint32_t memory_type_idx;
+        vk::MemoryPropertyFlags property_flags = *req_flags_list.begin();
+        for (memory_type_idx = 0; memory_type_idx < 32; ++memory_type_idx) {
+            if (!(host_pointer_props.memoryTypeBits & (1u << memory_type_idx))) {
+                continue;
+            }
+            if (!(mem_req.memoryTypeBits & (1u << memory_type_idx))) {
+                continue;
+            }
+
+            vk::MemoryType memory_type = mem_props.memoryTypes[memory_type_idx];
+            // check for visible+coherent+cached. Other flags (e.g. devicelocal) are allowed
+            if ((memory_type.propertyFlags & property_flags) == property_flags) {
+                property_flags = memory_type.propertyFlags;
+                break;
+            }
+        }
+        if (memory_type_idx == 32) {
+            GGML_LOG_WARN("ggml_vulkan: Memory type for host allocation not found\n");
+            device->device.destroyBuffer(buf->buffer);
+            return {};
+        }
+
+        buf->memory_property_flags = mem_props.memoryTypes[memory_type_idx].propertyFlags;
+        try {
+            vk::ImportMemoryHostPointerInfoEXT import_info;
+            import_info.handleType = vk::ExternalMemoryHandleTypeFlagBits::eHostAllocationEXT;
+            import_info.pHostPointer = import_ptr;
+            import_info.setPNext(&mem_flags_info);
+            buf->device_memory = device->device.allocateMemory({ size, memory_type_idx, &import_info });
+        } catch (const vk::SystemError& e) {
+        }
+    } else {
+        for (auto it = req_flags_list.begin(); it != req_flags_list.end(); it++) {
+            const auto & req_flags = *it;
+
+            const std::vector<uint32_t> memory_type_indices = ggml_vk_find_memory_properties(&mem_props, &mem_req, req_flags);
+
+            if (memory_type_indices.empty()) {
+                continue;
+            }
+
+            bool done = false;
+
+            for (auto mtype_it = memory_type_indices.begin(); mtype_it != memory_type_indices.end(); mtype_it++) {
+                try {
+                    buf->device_memory = device->device.allocateMemory({ mem_req.size, *mtype_it, &mem_flags_info });
+                    buf->memory_property_flags = mem_props.memoryTypes[*mtype_it].propertyFlags;
+                    done = true;
+                    break;
+                } catch (const vk::SystemError& e) {
+                    // loop and retry
+                    // during last attempt throw the exception
+                    if (it + 1 == req_flags_list.end() && mtype_it + 1 == memory_type_indices.end()) {
+                        device->device.destroyBuffer(buf->buffer);
+                        throw e;
+                    }
+                }
+            }
+
+            if (done) {
+                break;
+            }
+        }
+    }
+
+    if (!buf->device_memory) {
+        device->device.destroyBuffer(buf->buffer);
+        throw vk::OutOfDeviceMemoryError("No suitable memory type found");
+    }
+
+    buf->ptr = nullptr;
+
+    if (import_ptr) {
+        buf->ptr = import_ptr;
+    } else {
+        if (buf->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible) {
+            buf->ptr = device->device.mapMemory(buf->device_memory, 0, VK_WHOLE_SIZE);
+        }
+    }
+
+    device->device.bindBufferMemory(buf->buffer, buf->device_memory, 0);
+
+    buf->device = device;
+    buf->size = size;
+
+    if (device->buffer_device_address) {
+        const vk::BufferDeviceAddressInfo addressInfo(buf->buffer);
+        buf->bda_addr = device->device.getBufferAddress(addressInfo);
+    }
+
+    device->memory_logger->log_allocation(buf, size);
+
+    return buf;
+}
+
+vk_buffer ggml_vk_create_buffer_check(vk_device& device, size_t size, vk::MemoryPropertyFlags req_flags, vk::MemoryPropertyFlags fallback_flags) {
+    try {
+        return ggml_vk_create_buffer(device, size, {req_flags, fallback_flags});
+    } catch (const vk::SystemError& e) {
+        std::cerr << "ggml_vulkan: Memory allocation of size " << size << " failed." << std::endl;
+        std::cerr << "ggml_vulkan: " << e.what() << std::endl;
+        throw e;
+    }
+}
+
+vk_buffer ggml_vk_create_buffer_device(vk_device& device, size_t size) {
+    vk_buffer buf;
+    try {
+        if (device->prefer_host_memory) {
+            buf = ggml_vk_create_buffer(device, size, {vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent,
+                                                       vk::MemoryPropertyFlagBits::eDeviceLocal});
+        } else if (device->uma) {
+            // On UMA, prefer host-visible memory so direct tensor borrowing works.
+            // If unavailable, fall back to device-local memory.
+            buf = ggml_vk_create_buffer(device, size, {vk::MemoryPropertyFlagBits::eDeviceLocal | vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent,
+                                                       vk::MemoryPropertyFlagBits::eDeviceLocal,
+                                                       vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent});
+        } else if (device->disable_host_visible_vidmem) {
+            if (device->allow_sysmem_fallback) {
+                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});
+            }
+        } else {
+            // use rebar if available, otherwise fallback to device only visible memory
+            if (device->allow_sysmem_fallback) {
+                buf = ggml_vk_create_buffer(device, size, {vk::MemoryPropertyFlagBits::eDeviceLocal | vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent,
+                                                           vk::MemoryPropertyFlagBits::eDeviceLocal,
+                                                           vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent});
+            } else {
+                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;
+        std::cerr << "ggml_vulkan: " << e.what() << std::endl;
+        throw e;
+    }
+
+    return buf;
+}
+
+void ggml_vk_destroy_buffer(vk_buffer& buf) {
+    if (buf == nullptr) {
+        return;
+    }
+
+    if (buf->device != nullptr) {
+        buf->device->memory_logger->log_deallocation(buf);
+    }
+
+    buf.reset();
+}
+
+void * ggml_vk_host_malloc(vk_device& device, size_t size) {
+    VK_LOG_MEMORY("ggml_vk_host_malloc(" << size << ")");
+    vk_buffer buf = ggml_vk_create_buffer(device, size,
+        {vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent | vk::MemoryPropertyFlagBits::eHostCached,
+         vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent});
+
+    if(!(buf->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible)) {
+        fprintf(stderr, "WARNING: failed to allocate %.2f MB of pinned memory\n",
+            size/1024.0/1024.0);
+        device->device.freeMemory(buf->device_memory);
+        device->device.destroyBuffer(buf->buffer);
+        return nullptr;
+    }
+
+    std::lock_guard<std::shared_mutex> guard(device->pinned_memory_mutex);
+    device->pinned_memory.push_back(std::make_tuple(buf->ptr, size, buf));
+
+    return buf->ptr;
+}
+
+void ggml_vk_host_free(vk_device& device, void* ptr) {
+    if (ptr == nullptr) {
+        return;
+    }
+    VK_LOG_MEMORY("ggml_vk_host_free(" << ptr << ")");
+    std::lock_guard<std::shared_mutex> guard(device->pinned_memory_mutex);
+
+    vk_buffer buf;
+    size_t index;
+    for (size_t i = 0; i < device->pinned_memory.size(); i++) {
+        const uint8_t* addr = (const uint8_t*) std::get<0>(device->pinned_memory[i]);
+        const uint8_t* endr = addr + std::get<1>(device->pinned_memory[i]);
+        if (ptr >= addr && ptr < endr) {
+            buf = std::get<2>(device->pinned_memory[i]);
+            index = i;
+            break;
+        }
+    }
+    if (buf == nullptr) {
+        fprintf(stderr, "WARNING: failed to free pinned memory: memory not in map\n");
+        return;
+    }
+
+    ggml_vk_destroy_buffer(buf);
+
+    device->pinned_memory.erase(device->pinned_memory.begin() + index);
+}
+
+void ggml_vk_host_get(const vk_device& device, const void * ptr, vk_buffer& buf, size_t& buf_offset) {
+    std::shared_lock<std::shared_mutex> guard(device->pinned_memory_mutex);
+    buf = nullptr;
+    buf_offset = 0;
+    for (size_t i = 0; i < device->pinned_memory.size(); i++) {
+        const uint8_t* addr = (const uint8_t*) std::get<0>(device->pinned_memory[i]);
+        const uint8_t* endr = addr + std::get<1>(device->pinned_memory[i]);
+        if (ptr >= addr && ptr < endr) {
+            buf = std::get<2>(device->pinned_memory[i]);
+            buf_offset = ((const uint8_t *)ptr) - addr;
+            break;
+        }
+    }
+}
+
+void ggml_vk_ensure_sync_staging_buffer(vk_device& device, size_t size) {
+    if (device->sync_staging == nullptr || device->sync_staging->size < size) {
+        VK_LOG_MEMORY("ggml_vk_ensure_sync_staging_buffer(" << size << ")");
+        ggml_vk_destroy_buffer(device->sync_staging);
+        device->sync_staging = ggml_vk_create_buffer_check(device, size,
+            vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent | vk::MemoryPropertyFlagBits::eHostCached,
+            vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent);
+    }
+}
+
+void ggml_vk_ensure_sync_staging_buffer(ggml_backend_vk_context * ctx, size_t size) {
+    if (ctx->sync_staging == nullptr || ctx->sync_staging->size < size) {
+        VK_LOG_MEMORY("ggml_vk_ensure_sync_staging_buffer(" << size << ")");
+        ggml_vk_destroy_buffer(ctx->sync_staging);
+        ctx->sync_staging = ggml_vk_create_buffer_check(ctx->device, size,
+            vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent | vk::MemoryPropertyFlagBits::eHostCached,
+            vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent);
+    }
+}
+
+static void ggml_vk_buffer_write_nc_async(ggml_backend_vk_context * ctx, vk_context& subctx, vk_buffer& dst, size_t offset, const ggml_tensor * tensor, bool sync_staging = false) {
+    VK_LOG_DEBUG("ggml_vk_buffer_write_nc_async(" << tensor << ")");
+    GGML_ASSERT(!ggml_is_contiguous(tensor));
+    // Buffer is already mapped
+    if(dst->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible) {
+        std::cerr << "ggml_vulkan: buffer_write_nc_async dst buffer is host_visible. Use synchronous write." << std::endl;
+        GGML_ABORT("fatal error");
+    }
+    // Check if src is pinned memory
+    vk_buffer buf = nullptr;
+    size_t buf_offset = 0;
+    ggml_vk_host_get(ctx->device, tensor->data, buf, buf_offset);
+
+    const uint64_t ne0 = tensor->ne[0];
+    const uint64_t ne1 = tensor->ne[1];
+    const uint64_t ne2 = tensor->ne[2];
+    const uint64_t ne3 = tensor->ne[3];
+    const uint64_t nb0 = tensor->nb[0];
+    const uint64_t nb1 = tensor->nb[1];
+    const uint64_t nb2 = tensor->nb[2];
+    const uint64_t nb3 = tensor->nb[3];
+    const ggml_type type = tensor->type;
+    const uint64_t ts = ggml_type_size(type);
+    const uint64_t bs = ggml_blck_size(type);
+
+    const uint64_t dstnb0 = ts;
+    const uint64_t dstnb1 = dstnb0*(ne0/bs);
+    const uint64_t dstnb2 = dstnb1*ne1;
+    const uint64_t dstnb3 = dstnb2*ne2;
+
+    const uint64_t ne = ggml_nelements(tensor);
+
+    if (buf != nullptr) {
+        // Memory is pinned, use as staging buffer
+        std::vector<vk::BufferCopy> slices;
+
+        for (uint64_t i3 = 0; i3 < ne3; i3++) {
+            for (uint64_t i2 = 0; i2 < ne2; i2++) {
+                // Find longest contiguous slice
+                if (ne1*nb1 == dstnb2) {
+                    slices.push_back({ buf_offset + i3*nb3 + i2*nb2, offset + i3*dstnb3 + i2*dstnb2, dstnb2 });
+                } else {
+                    for (uint64_t i1 = 0; i1 < ne1; i1++) {
+                        if (ne0*nb0/bs == dstnb1) {
+                            slices.push_back({ buf_offset + i3*nb3 + i2*nb2 + i1*nb1, offset + i3*dstnb3 + i2*dstnb2 + i1*dstnb1, dstnb1 });
+                        } else {
+                            const uint64_t s_off = buf_offset + i3*nb3 + i2*nb2 + i1*nb1;
+                            const uint64_t d_off = offset + i3*dstnb3 + i2*dstnb2 + i1*dstnb1;
+                            for (uint64_t i0 = 0; i0 < ne0; i0++) {
+                                slices.push_back({ s_off + i0*nb0, d_off + i0*dstnb0, dstnb0 });
+                            }
+                        }
+                    }
+                }
+            }
+        }
+
+        ggml_vk_sync_buffers(ctx, subctx);
+        subctx->s->buffer->buf.copyBuffer(buf->buffer, dst->buffer, slices);
+        return;
+    }
+
+    if (!sync_staging) {
+        GGML_ABORT("Asynchronous write to non-pinned memory not supported");
+    }
+
+    // Staging buffer required
+    vk_buffer& staging = ctx->device->sync_staging;
+    const uint64_t copy_size = ts*ne/bs;
+    ggml_vk_ensure_sync_staging_buffer(ctx->device, copy_size);
+    VkBufferCopy buf_copy{ 0, offset, copy_size };
+
+    ggml_vk_sync_buffers(ctx, subctx);
+    vkCmdCopyBuffer(subctx->s->buffer->buf, (VkBuffer)staging->buffer, (VkBuffer)dst->buffer, 1, &buf_copy);
+
+    for (uint64_t i3 = 0; i3 < ne3; i3++) {
+        for (uint64_t i2 = 0; i2 < ne2; i2++) {
+            // Find longest contiguous slice
+            if (ne1*nb1 == dstnb2) {
+                deferred_memcpy((uint8_t *)staging->ptr + i3*dstnb3 + i2*dstnb2, (const uint8_t *) tensor->data + buf_offset + i3*nb3 + i2*nb2, dstnb2, &subctx->in_memcpys);
+            } else {
+                for (uint64_t i1 = 0; i1 < ne1; i1++) {
+                    if (ne0*nb0/bs == dstnb1) {
+                        deferred_memcpy((uint8_t *)staging->ptr + i3*dstnb3 + i2*dstnb2 + i1*dstnb1, (const uint8_t *) tensor->data + buf_offset + i3*nb3 + i2*nb2 + i1*nb1, dstnb1, &subctx->in_memcpys);
+                    } else {
+                        const uint64_t s_off = buf_offset + i3*nb3 + i2*nb2 + i1*nb1;
+                        const uint64_t d_off = i3*dstnb3 + i2*dstnb2 + i1*dstnb1;
+                        for (uint64_t i0 = 0; i0 < ne0; i0++) {
+                            deferred_memcpy((uint8_t *)staging->ptr + d_off + i0*dstnb0, (const uint8_t *) tensor->data + s_off + i0*nb0, dstnb0, &subctx->in_memcpys);
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+
+bool ggml_vk_buffer_write_2d_async(vk_context subctx, vk_buffer& dst, size_t offset, const void * src, size_t spitch, size_t dpitch, size_t width, size_t height, bool sync_staging) {
+    VK_LOG_DEBUG("ggml_vk_buffer_write_2d_async(" << width << ", " << height << ")");
+    // Check if src is pinned memory
+    vk_buffer buf = nullptr;
+    size_t buf_offset = 0;
+    ggml_vk_host_get(dst->device, src, buf, buf_offset);
+
+    if (buf != nullptr) {
+        // Memory is pinned, use as staging buffer
+        std::vector<vk::BufferCopy> slices(1);
+        if (width == spitch && width == dpitch) {
+            // Only do single write if stride is equal
+            slices[0].srcOffset = buf_offset;
+            slices[0].dstOffset = offset;
+            slices[0].size = width * height;
+        } else {
+            slices.resize(height);
+            for (size_t i = 0; i < height; i++) {
+                slices[i].srcOffset = buf_offset + i * spitch;
+                slices[i].dstOffset = offset + i * dpitch;
+                slices[i].size = width;
+            }
+        }
+
+        ggml_vk_sync_buffers(nullptr, subctx);
+        subctx->s->buffer->buf.copyBuffer(buf->buffer, dst->buffer, slices);
+        return true;
+    }
+    VK_LOG_DEBUG("STAGING");
+
+    if (!sync_staging) {
+        // copy was not handled caller needs to fall back
+        return false;
+    }
+
+    // Staging buffer required
+    const size_t staging_size = width * height;
+    ggml_vk_ensure_sync_staging_buffer(dst->device, staging_size);
+
+    vk_buffer& staging_buffer = dst->device->sync_staging;
+
+    std::vector<vk::BufferCopy> slices(1);
+    if (width == dpitch) {
+        slices[0].srcOffset = 0;
+        slices[0].dstOffset = offset;
+        slices[0].size = staging_size;
+    } else {
+        slices.resize(height);
+        for (size_t i = 0; i < height; i++) {
+            slices[i].srcOffset = i * width;
+            slices[i].dstOffset = offset + i * dpitch;
+            slices[i].size = width;
+        }
+    }
+
+    ggml_vk_sync_buffers(nullptr, subctx);
+    subctx->s->buffer->buf.copyBuffer(staging_buffer->buffer, dst->buffer, slices);
+
+    if (width == spitch) {
+        deferred_memcpy((uint8_t *)staging_buffer->ptr, src, staging_size, &subctx->in_memcpys);
+    } else {
+        for (size_t i = 0; i < height; i++) {
+            deferred_memcpy((uint8_t *)staging_buffer->ptr + i * width, (const uint8_t *) src + i * spitch, width, &subctx->in_memcpys);
+        }
+    }
+    return true;
+}
+
+bool ggml_vk_buffer_write_async(vk_context subctx, vk_buffer& dst, size_t offset, const void * src, size_t size, bool sync_staging) {
+    VK_LOG_DEBUG("ggml_vk_buffer_write_async(" << size << ")");
+    return ggml_vk_buffer_write_2d_async(subctx, dst, offset, src, size, size, size, 1, sync_staging);
+}
+
+void ggml_vk_buffer_write_2d(vk_buffer& dst, size_t offset, const void * src, size_t spitch, size_t dpitch, size_t width, size_t height) {
+    VK_LOG_DEBUG("ggml_vk_buffer_write_2d(" << width << ", " << height << ")");
+    // Buffer is already mapped
+    if(dst->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible) {
+        GGML_ASSERT(dst->memory_property_flags & vk::MemoryPropertyFlagBits::eHostCoherent);
+
+        if (width == spitch && width == dpitch) {
+            memcpy((uint8_t *)dst->ptr + offset, src, width * height);
+        } else {
+            for (size_t i = 0; i < height; i++) {
+                memcpy((uint8_t *)dst->ptr + offset + i * dpitch, (const uint8_t *) src + i * spitch, width);
+            }
+        }
+    } else {
+        std::lock_guard<std::recursive_mutex> guard(dst->device->mutex);
+
+        vk_context subctx = ggml_vk_create_temporary_context(dst->device->transfer_queue->cmd_pool);
+        ggml_vk_ctx_begin(dst->device, subctx);
+        bool ret = ggml_vk_buffer_write_2d_async(subctx, dst, offset, src, spitch, dpitch, width, height, true);
+        GGML_ASSERT(ret);
+        ggml_vk_ctx_end(subctx);
+
+        for (auto& cpy : subctx->in_memcpys) {
+            memcpy(cpy.dst, cpy.src, cpy.n);
+        }
+
+        for (auto& mset : subctx->memsets) {
+            memset(mset.dst, mset.val, mset.n);
+        }
+
+        ggml_vk_submit(subctx, dst->device->fence);
+        VK_CHECK(dst->device->device.waitForFences({ dst->device->fence }, true, UINT64_MAX), "vk_buffer_write_2d waitForFences", dst->device);
+        dst->device->device.resetFences({ dst->device->fence });
+        ggml_vk_queue_command_pools_cleanup(dst->device);
+    }
+}
+
+void ggml_vk_buffer_write(vk_buffer& dst, size_t offset, const void * src, size_t size) {
+    VK_LOG_DEBUG("ggml_vk_buffer_write(" << size << ")");
+    ggml_vk_buffer_write_2d(dst, offset, src, size, size, size, 1);
+}
+
+bool ggml_vk_buffer_read_2d_async(vk_context subctx, vk_buffer& src, size_t offset, void * dst, size_t spitch, size_t dpitch, size_t width, size_t height, bool sync_staging) {
+    VK_LOG_DEBUG("ggml_vk_buffer_read_2d_async(offset=" << offset << ", width=" << width << ", height=" << height << ")");
+    GGML_ASSERT(width > 0);
+    GGML_ASSERT(height > 0);
+    GGML_ASSERT(src != nullptr);
+
+    // TODO: staging_offset is not used
+
+    // Check if dst is pinned memory
+    vk_buffer buf = nullptr;
+    size_t buf_offset = 0;
+    ggml_vk_host_get(src->device, dst, buf, buf_offset);
+
+    std::vector<vk::BufferCopy> slices(1);
+    if (width == spitch && width == dpitch) {
+        // Only do single write if stride is equal
+        slices[0].srcOffset = offset;
+        slices[0].dstOffset = buf_offset;
+        slices[0].size = width * height;
+    } else {
+        slices.resize(height);
+        for (size_t i = 0; i < height; i++) {
+            slices[i].srcOffset = offset + i * spitch;
+            slices[i].dstOffset = buf_offset + i * dpitch;
+            slices[i].size = width;
+        }
+    }
+
+    if (buf != nullptr) {
+        // Memory is pinned, use as staging buffer
+        ggml_vk_sync_buffers(nullptr, subctx);
+        subctx->s->buffer->buf.copyBuffer(src->buffer, buf->buffer, slices);
+
+        return true;
+    }
+    VK_LOG_DEBUG("STAGING");
+
+    if (!sync_staging) {
+        // copy was not handled caller needs to fall back
+        return false;
+    }
+
+    // Fall back to staging buffer
+    const size_t staging_size = width * height;
+    ggml_vk_ensure_sync_staging_buffer(src->device, staging_size);
+
+    vk_buffer& staging_buffer = src->device->sync_staging;
+
+    std::vector<vk::BufferCopy> staging_slices(1);
+    if (width == spitch) {
+        staging_slices[0].srcOffset = offset;
+        staging_slices[0].dstOffset = 0;
+        staging_slices[0].size = staging_size;
+    } else {
+        staging_slices.resize(height);
+        for (size_t i = 0; i < height; i++) {
+            staging_slices[i].srcOffset = offset + i * spitch;
+            staging_slices[i].dstOffset = i * width;
+            staging_slices[i].size = width;
+        }
+    }
+
+    ggml_vk_sync_buffers(nullptr, subctx);
+    subctx->s->buffer->buf.copyBuffer(src->buffer, staging_buffer->buffer, staging_slices);
+
+    if (width == dpitch) {
+        deferred_memcpy(dst, staging_buffer->ptr, staging_size, &subctx->out_memcpys);
+    } else {
+        for (size_t i = 0; i < height; i++) {
+            deferred_memcpy((uint8_t *) dst + i * dpitch, (const uint8_t *) staging_buffer->ptr + i * width, width, &subctx->out_memcpys);
+        }
+    }
+    return true;
+}
+
+static bool ggml_vk_buffer_read_async(vk_context subctx, vk_buffer& src, size_t offset, void * dst, size_t size, bool sync_staging = false) {
+    return ggml_vk_buffer_read_2d_async(subctx, src, offset, dst, size, size, size, 1, sync_staging);
+}
+
+void ggml_vk_buffer_read_2d(vk_buffer& src, size_t offset, void * dst, size_t spitch, size_t dpitch, size_t width, size_t height) {
+    VK_LOG_DEBUG("ggml_vk_buffer_read_2d(" << src->buffer << ", " << offset << ", " << width << ", " << height << ")");
+
+    // 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);
+
+        std::lock_guard<std::recursive_mutex> guard(src->device->mutex);
+        vk_context subctx = ggml_vk_create_temporary_context(src->device->compute_queue->cmd_pool);
+        ggml_vk_ctx_begin(src->device, subctx);
+        subctx->s->buffer->buf.pipelineBarrier(
+            vk::PipelineStageFlagBits::eComputeShader | vk::PipelineStageFlagBits::eTransfer,
+            vk::PipelineStageFlagBits::eHost,
+            {},
+            { { vk::AccessFlagBits::eShaderWrite | vk::AccessFlagBits::eTransferWrite,
+                vk::AccessFlagBits::eHostRead } },
+            {}, {});
+        ggml_vk_ctx_end(subctx);
+        ggml_vk_submit(subctx, src->device->fence);
+        VK_CHECK(src->device->device.waitForFences({ src->device->fence }, true, UINT64_MAX),
+                 "vk_buffer_read_2d uma waitForFences", src->device);
+        src->device->device.resetFences({ src->device->fence });
+        ggml_vk_queue_command_pools_cleanup(src->device);
+
+        if (width == spitch && width == dpitch) {
+            memcpy(dst, (const uint8_t *) src->ptr + offset, width * height);
+        } else {
+            for (size_t i = 0; i < height; i++) {
+                memcpy((uint8_t *) dst + i * dpitch, (const uint8_t *) src->ptr + offset + i * spitch, width);
+            }
+        }
+    } else {
+        std::lock_guard<std::recursive_mutex> guard(src->device->mutex);
+
+        vk_context subctx = ggml_vk_create_temporary_context(src->device->transfer_queue->cmd_pool);
+        ggml_vk_ctx_begin(src->device, subctx);
+        bool ret = ggml_vk_buffer_read_2d_async(subctx, src, offset, dst, spitch, dpitch, width, height, true);
+        GGML_ASSERT(ret);
+        ggml_vk_ctx_end(subctx);
+
+        ggml_vk_submit(subctx, src->device->fence);
+        VK_CHECK(src->device->device.waitForFences({ src->device->fence }, true, UINT64_MAX), "vk_buffer_read_2d waitForFences", src->device);
+        src->device->device.resetFences({ src->device->fence });
+        ggml_vk_queue_command_pools_cleanup(src->device);
+
+        for (auto& cpy : subctx->out_memcpys) {
+            memcpy(cpy.dst, cpy.src, cpy.n);
+        }
+    }
+}
+
+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 << ")");
+    ggml_vk_buffer_read_2d(src, offset, dst, size, size, size, 1);
+}
+
+void ggml_vk_buffer_copy_async(vk_context& ctx, vk_buffer& dst, size_t dst_offset, vk_buffer& src, size_t src_offset, size_t size) {
+    VK_LOG_DEBUG("ggml_vk_buffer_copy_async(" << size << ")");
+    // Make sure both buffers are on same device
+    GGML_ASSERT(src->device == dst->device);
+
+    VkBufferCopy bc{ src_offset, dst_offset, size };
+
+    vkCmdCopyBuffer(ctx->s->buffer->buf, (VkBuffer)src->buffer, (VkBuffer)dst->buffer, 1, &bc);
+}
+
+void ggml_vk_buffer_copy(vk_buffer& dst, size_t dst_offset, vk_buffer& src, size_t src_offset, size_t size) {
+    if (src->device == dst->device) {
+        std::lock_guard<std::recursive_mutex> guard(src->device->mutex);
+        VK_LOG_DEBUG("ggml_vk_buffer_copy(SINGLE_DEVICE, " << size << ")");
+        // Copy within the device
+        vk_context subctx = ggml_vk_create_temporary_context(src->device->transfer_queue->cmd_pool);
+        ggml_vk_ctx_begin(src->device, subctx);
+        ggml_vk_buffer_copy_async(subctx, dst, dst_offset, src, src_offset, size);
+        ggml_vk_ctx_end(subctx);
+        ggml_vk_submit(subctx, src->device->fence);
+        VK_CHECK(src->device->device.waitForFences({ src->device->fence }, true, UINT64_MAX), "vk_buffer_copy waitForFences", src->device);
+        src->device->device.resetFences({ src->device->fence });
+        ggml_vk_queue_command_pools_cleanup(src->device);
+    } else {
+        VK_LOG_DEBUG("ggml_vk_buffer_copy(MULTI_DEVICE, " << size << ")");
+        // Copy device to device
+        ggml_vk_ensure_sync_staging_buffer(src->device, size);
+
+        // Copy to src staging buffer
+        ggml_vk_buffer_copy(src->device->sync_staging, 0, src, src_offset, size);
+        // Copy to dst buffer
+        ggml_vk_buffer_write(dst, dst_offset, src->device->sync_staging->ptr, size);
+    }
+}
+
+void ggml_vk_buffer_memset_async(vk_context& ctx, vk_buffer& dst, size_t offset, uint32_t c, size_t size) {
+    VK_LOG_DEBUG("ggml_vk_buffer_memset_async(" << offset << ", " << c << ", " << size << ")");
+
+    if (dst->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible &&
+        dst->device->uma) {
+        deferred_memset((uint8_t*)dst->ptr + offset, c, size, &ctx->memsets);
+        return;
+    }
+
+    // Fall back to GPU fillBuffer for non-UMA or non-host-visible buffers
+    ctx->s->buffer->buf.fillBuffer(dst->buffer, offset, size, c);
+}
+
+void ggml_vk_buffer_memset(vk_buffer& dst, size_t offset, uint32_t c, size_t size) {
+    VK_LOG_DEBUG("ggml_vk_buffer_memset(" << offset << ", " << c << ", " << size << ")");
+
+    if (dst->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible &&
+        dst->device->uma) {
+        memset((uint8_t*)dst->ptr + offset, c, size);
+        return;
+    }
+
+    std::lock_guard<std::recursive_mutex> guard(dst->device->mutex);
+    vk_context subctx = ggml_vk_create_temporary_context(dst->device->transfer_queue->cmd_pool);
+    ggml_vk_ctx_begin(dst->device, subctx);
+    subctx->s->buffer->buf.fillBuffer(dst->buffer, offset, size, c);
+    ggml_vk_ctx_end(subctx);
+
+    ggml_vk_submit(subctx, dst->device->fence);
+    VK_CHECK(dst->device->device.waitForFences({ dst->device->fence }, true, UINT64_MAX), "vk_memset waitForFences", dst->device);
+    dst->device->device.resetFences({ dst->device->fence });
+    ggml_vk_queue_command_pools_cleanup(dst->device);
+}
+
+ggml_backend_buffer_i ggml_backend_vk_buffer_interface = {
+    /* .free_buffer     = */ ggml_backend_vk_buffer_free_buffer,
+    /* .get_base        = */ ggml_backend_vk_buffer_get_base,
+    /* .init_tensor     = */ ggml_backend_vk_buffer_init_tensor,
+    /* .memset_tensor   = */ ggml_backend_vk_buffer_memset_tensor,
+    /* .set_tensor      = */ ggml_backend_vk_buffer_set_tensor,
+    /* .get_tensor      = */ ggml_backend_vk_buffer_get_tensor,
+    /* .set_tensor_2d   = */ ggml_backend_vk_buffer_set_tensor_2d,
+    /* .get_tensor_2d   = */ ggml_backend_vk_buffer_get_tensor_2d,
+    /* .cpy_tensor      = */ ggml_backend_vk_buffer_cpy_tensor,
+    /* .clear           = */ ggml_backend_vk_buffer_clear,
+    /* .reset           = */ NULL,
+};
+
+vk_buffer ggml_vk_buffer_from_host_ptr(vk_device & device, void * ptr, size_t size) {
+    if (!device->external_memory_host) {
+        return {};
+    }
+
+    uintptr_t uptr = reinterpret_cast<uintptr_t>(ptr);
+    if (uptr & (device->min_imported_host_pointer_alignment - 1)) {
+        return {};
+    }
+    if (size & (device->min_imported_host_pointer_alignment - 1)) {
+        return {};
+    }
+
+    const vk::MemoryPropertyFlags property_flags = vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent | vk::MemoryPropertyFlagBits::eHostCached;
+
+    vk_buffer buf {};
+    try {
+        buf = ggml_vk_create_buffer(device, size, { property_flags }, ptr);
+    } catch (vk::SystemError& e) {
+        GGML_LOG_WARN("ggml_vulkan: Failed ggml_vk_create_buffer (%s)\n", e.what());
+    }
+
+    return buf;
+}
+

ggml/src/ggml-vulkan/ggml-vulkan-common.h

@@ -0,0 +1,282 @@
+#pragma once
+#include "ggml-vulkan-push-constants.h"
+
+// shared globals
+extern ggml_backend_buffer_type_i ggml_backend_vk_buffer_type_interface;
+extern bool vk_memory_logger_enabled;
+extern bool vk_perf_logger_enabled;
+extern bool vk_perf_logger_concurrent;
+extern bool vk_enable_sync_logger;
+extern uint32_t vk_perf_logger_frequency;
+extern std::string vk_pipeline_stats_filter;
+extern void * const vk_ptr_base;
+extern vk_instance_t vk_instance;
+extern ggml_backend_buffer_i ggml_backend_vk_buffer_interface;
+
+// instance
+vk_device ggml_vk_get_device(size_t idx);
+DispatchLoaderDynamic & ggml_vk_default_dispatcher();
+void ggml_vk_instance_init();
+void ggml_vk_init(ggml_backend_vk_context * ctx, size_t idx);
+int ggml_vk_get_device_count();
+void ggml_vk_get_device_description(int device, char * description, size_t description_size);
+bool ggml_vk_instance_layer_settings_available();
+bool ggml_vk_instance_portability_enumeration_ext_available(const std::vector<vk::ExtensionProperties>& instance_extensions);
+bool ggml_vk_instance_debug_utils_ext_available(const std::vector<vk::ExtensionProperties> & instance_extensions);
+bool ggml_vk_device_is_supported(const vk::PhysicalDevice & vkdev);
+bool ggml_vk_khr_cooperative_matrix_support(const vk::PhysicalDeviceProperties& props, const vk::PhysicalDeviceDriverProperties& driver_props, vk_device_architecture arch);
+uint32_t ggml_vk_intel_shader_core_count(const vk::PhysicalDevice& vkdev);
+bool ggml_vk_intel_windows_driver_in_range(uint32_t driver_version, uint32_t lower_major, uint32_t lower_minor, uint32_t upper_major, uint32_t upper_minor);
+
+// shaders
+void ggml_vk_destroy_pipeline(vk::Device& device, vk_pipeline& pipeline);
+vk_fa_tuning_params get_fa_tuning_params(const vk_device& device, uint32_t hsk, uint32_t hsv, uint32_t n_rows, uint32_t n_kv, ggml_type k_type, ggml_type v_type, bool f32acc);
+vk_fa_pipeline_state get_fa_pipeline_state(const vk_device& device, const vk_fa_tuning_params& params, uint32_t hsk, uint32_t hsv, bool aligned, bool f32acc, bool use_mask, bool use_mask_opt, bool use_logit_softcap, ggml_type k_type, ggml_type v_type);
+uint32_t get_subgroup_size(const std::string &pipeline_name, const vk_device_architecture &arch);
+void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested = nullptr);
+bool ggml_vk_flash_attn_scalar_shmem_support(const vk_device& device, const vk_fa_tuning_params& params, uint32_t hsk, uint32_t hsv, bool f32acc, ggml_type k_type, ggml_type v_type);
+bool ggml_vk_flash_attn_coopmat_shmem_support(const vk_device& device, const vk_fa_tuning_params& params, uint32_t hsk, uint32_t hsv, bool f32acc, ggml_type k_type = GGML_TYPE_F16, ggml_type v_type = GGML_TYPE_F16);
+
+// buffers
+vk_buffer ggml_vk_create_buffer_check(vk_device& device, size_t size, vk::MemoryPropertyFlags req_flags, vk::MemoryPropertyFlags fallback_flags = vk::MemoryPropertyFlags(0));
+vk_buffer ggml_vk_create_buffer_device(vk_device& device, size_t size);
+void ggml_vk_destroy_buffer(vk_buffer& buf);
+void * ggml_vk_host_malloc(vk_device& device, size_t size);
+void ggml_vk_host_free(vk_device& device, void* ptr);
+void ggml_vk_host_get(const vk_device& device, const void * ptr, vk_buffer& buf, size_t& buf_offset);
+void ggml_vk_ensure_sync_staging_buffer(vk_device& device, size_t size);
+void ggml_vk_ensure_sync_staging_buffer(ggml_backend_vk_context * ctx, size_t size);
+bool ggml_vk_buffer_write_2d_async(vk_context subctx, vk_buffer& dst, size_t offset, const void * src, size_t spitch, size_t dpitch, size_t width, size_t height, bool sync_staging = false);
+bool ggml_vk_buffer_write_async(vk_context subctx, vk_buffer& dst, size_t offset, const void * src, size_t size, bool sync_staging = false);
+void ggml_vk_buffer_write_2d(vk_buffer& dst, size_t offset, const void * src, size_t spitch, size_t dpitch, size_t width, size_t height);
+void ggml_vk_buffer_write(vk_buffer& dst, size_t offset, const void * src, size_t size);
+bool ggml_vk_buffer_read_2d_async(vk_context subctx, vk_buffer& src, size_t offset, void * dst, size_t spitch, size_t dpitch, size_t width, size_t height, bool sync_staging = false);
+void ggml_vk_buffer_read_2d(vk_buffer& src, size_t offset, void * dst, size_t spitch, size_t dpitch, size_t width, size_t height);
+void ggml_vk_buffer_read(vk_buffer& src, size_t offset, void * dst, size_t size);
+void ggml_vk_buffer_copy_async(vk_context& ctx, vk_buffer& dst, size_t dst_offset, vk_buffer& src, size_t src_offset, size_t size);
+void ggml_vk_buffer_copy(vk_buffer& dst, size_t dst_offset, vk_buffer& src, size_t src_offset, size_t size);
+void ggml_vk_buffer_memset_async(vk_context& ctx, vk_buffer& dst, size_t offset, uint32_t c, size_t size);
+void ggml_vk_buffer_memset(vk_buffer& dst, size_t offset, uint32_t c, size_t size);
+vk_buffer ggml_vk_buffer_from_host_ptr(vk_device & device, void * ptr, size_t size);
+
+// pipelines
+uint64_t vk_tensor_offset(const ggml_tensor * tensor);
+uint32_t get_misalign_bytes(const ggml_backend_vk_context * ctx, const ggml_tensor * t);
+void ggml_vk_wait_for_fence(ggml_backend_vk_context * ctx);
+void ggml_pipeline_request_descriptor_sets(ggml_backend_vk_context *ctx, vk_pipeline& pipeline, uint32_t n);
+void ggml_pipeline_allocate_descriptor_sets(ggml_backend_vk_context * ctx);
+void ggml_vk_submit(vk_context& ctx, vk::Fence fence);
+uint32_t ggml_vk_find_queue_family_index(std::vector<vk::QueueFamilyProperties>& queue_family_props, const vk::QueueFlags& required, const vk::QueueFlags& avoid, int32_t compute_index, uint32_t min_num_queues);
+std::unique_ptr<vk_queue> ggml_vk_create_queue(vk_device& device, uint32_t queue_family_index, uint32_t queue_index, vk::PipelineStageFlags&& stage_flags, bool transfer_only);
+std::unique_ptr<vk_queue> ggml_vk_create_aliased_queue(vk_device& device, const std::unique_ptr<vk_queue>& source);
+vk_context ggml_vk_create_context(ggml_backend_vk_context * ctx, vk_command_pool& p);
+vk_context ggml_vk_create_temporary_context(vk_command_pool& p);
+void ggml_vk_command_pool_cleanup(vk_device& device, vk_command_pool& p);
+void ggml_vk_queue_command_pools_cleanup(vk_device& device);
+vk_subbuffer ggml_vk_subbuffer(const ggml_backend_vk_context* ctx, const vk_buffer& buf, size_t offset = 0);
+void ggml_vk_sync_buffers(ggml_backend_vk_context* ctx, vk_context& subctx);
+void ggml_vk_set_event(vk_context& ctx, vk::Event& event);
+void ggml_vk_wait_events(vk_context& ctx, std::vector<vk::Event>&& events);
+vk_subbuffer ggml_vk_tensor_subbuffer(const ggml_backend_vk_context * ctx, const ggml_tensor * tensor, bool allow_misalign = false);
+void ggml_vk_cmd_label_begin(vk::CommandBuffer buf, const char * name);
+void ggml_vk_ctx_end(vk_context& ctx);
+void ggml_vk_ctx_begin(vk_device& device, vk_context& subctx);
+vk_context ggml_vk_get_compute_ctx(ggml_backend_vk_context * ctx);
+vk_context ggml_vk_get_transfer_ctx(ggml_backend_vk_context * ctx);
+bool ggml_vk_submit_transfer_ctx(ggml_backend_vk_context * ctx);
+size_t ggml_vk_align_size(size_t width, size_t align);
+void deferred_memcpy(void * dst, const void * src, size_t size, std::vector<vk_staging_memcpy>* memcpys = nullptr);
+void deferred_memset(void * dst, uint32_t val, size_t size, std::vector<vk_staging_memset>* memsets = nullptr);
+
+// matmul
+vk_pipeline ggml_vk_get_to_fp16(ggml_backend_vk_context * ctx, ggml_type type);
+void ggml_vk_matmul(ggml_backend_vk_context * ctx, vk_context& subctx, vk_pipeline& pipeline, vk_subbuffer&& a, vk_subbuffer&& b, vk_subbuffer&& d, vk_subbuffer&& split_k_buffer, uint32_t m, uint32_t n, uint32_t k, uint32_t stride_a, uint32_t stride_b, uint32_t stride_d, uint32_t batch_stride_a, uint32_t batch_stride_b, uint32_t batch_stride_d, uint32_t split_k, uint32_t batch, uint32_t ne02, uint32_t ne12, uint32_t broadcast2, uint32_t broadcast3, uint32_t padded_n);
+bool ggml_vk_dim01_contiguous(const ggml_tensor * tensor);
+vk_pipeline ggml_vk_get_cpy_pipeline(ggml_backend_vk_context * ctx, const ggml_tensor * src, const ggml_tensor * dst, ggml_type to);
+vk_pipeline ggml_vk_get_quantize_pipeline(ggml_backend_vk_context * ctx, ggml_type type);
+void ggml_vk_quantize_q8_1(ggml_backend_vk_context * ctx, vk_context& subctx, const vk_subbuffer & in, const vk_subbuffer & out, uint32_t ne);
+void ggml_vk_dsv4_hc_comb(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * mixes, const ggml_tensor * scale, const ggml_tensor * base, ggml_tensor * dst);
+void ggml_vk_dsv4_hc_pre(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * x, const ggml_tensor * weights, ggml_tensor * dst);
+void ggml_vk_dsv4_hc_post(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * x, const ggml_tensor * residual, const ggml_tensor * post, const ggml_tensor * comb, ggml_tensor * dst);
+void ggml_vk_mul_mat(ggml_backend_vk_context * ctx, vk_context& subctx, const struct ggml_cgraph * cgraph, int node_idx);
+bool ggml_vk_use_mul_mat_vec_id(const struct ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_mul_mat_id(ggml_backend_vk_context * ctx, vk_context& subctx, const struct ggml_cgraph * cgraph, int node_idx);
+
+// flash-attn
+void ggml_vk_flash_attn(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * q, const ggml_tensor * k, const ggml_tensor * v, const ggml_tensor * mask, const ggml_tensor * sinks, ggml_tensor * dst);
+
+// operators
+void ggml_vk_cpy_to_contiguous(ggml_backend_vk_context * ctx, vk_context& subctx, vk_pipeline pipeline, const ggml_tensor * tensor, const vk_subbuffer & in, const vk_subbuffer & out);
+bool ggml_vk_can_use_fwht(const ggml_backend_vk_context * ctx, const ggml_tensor * src1, const ggml_tensor * dst);
+void ggml_vk_fwht(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src, ggml_tensor * dst);
+void ggml_vk_get_rows(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_get_rows_back(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_acc(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_multi_add(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_add(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_out_prod(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_sub(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_mul(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+int ggml_vk_unary_mul_op_index(ggml_unary_op op);
+void ggml_vk_unary_mul(ggml_backend_vk_context * ctx, vk_context& subctx, const struct ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_div(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_add_id(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, ggml_tensor * dst);
+void ggml_vk_rwkv_wkv6(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_rwkv_wkv7(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_gated_linear_attn(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_lightning_indexer(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_gated_delta_net(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_ssm_scan(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_ssm_conv(ggml_backend_vk_context * ctx, vk_context& subctx, const struct ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_opt_step_adamw(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_opt_step_sgd(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, ggml_tensor * dst);
+void ggml_vk_concat(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_upscale(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_scale(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_sqr(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_sqrt(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_add1(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_arange(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_fill(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_sin(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_cos(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_log(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_tri(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_diag(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_clamp(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_pad(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_pad_reflect_1d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_roll(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_repeat(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_repeat_back(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_cpy(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_set_rows(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_silu_back(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_norm(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_group_norm(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+uint32_t ggml_vk_rms_partials_size(ggml_backend_vk_context * ctx, const ggml_tensor *node);
+void ggml_vk_rms_norm(ggml_backend_vk_context * ctx, vk_context& subctx, const struct ggml_cgraph * cgraph, int node_idx, float * op_params);
+void ggml_vk_rms_norm_back(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_l2_norm(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_unary(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_xielu(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_glu(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_diag_mask_inf(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_soft_max(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, ggml_tensor * dst);
+void ggml_vk_soft_max_back(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_topk_moe(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_rope(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_cgraph * cgraph, int node_idx, bool backprop);
+void ggml_vk_argsort(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_topk(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_topk_qsa(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_sum(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_sum_rows(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_mean(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_cumsum(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_cross_entropy_loss(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_cross_entropy_loss_back(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst);
+void ggml_vk_argmax(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_count_equal(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_solve_tri(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_im2col(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_im2col_3d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_timestep_embedding(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_conv_transpose_1d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_col2im_1d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_snake_dispatch_fused(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_pool_1d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_pool_2d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+void ggml_vk_conv_2d(ggml_backend_vk_context * ctx, vk_context & subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_conv_3d(ggml_backend_vk_context * ctx, vk_context & subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_conv_2d_dw(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst);
+void ggml_vk_leaky_relu(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst);
+
+// graph
+void ggml_vk_preallocate_buffers(ggml_backend_vk_context * ctx, vk_context subctx);
+bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_cgraph * cgraph, int node_idx, ggml_tensor *node_begin, int node_idx_begin, bool last_node, bool almost_ready, bool submit);
+void ggml_vk_compute_forward(ggml_backend_vk_context* ctx, ggml_cgraph * cgraph, ggml_tensor* tensor, int tensor_idx, bool almost_ready);
+void ggml_vk_graph_cleanup(ggml_backend_vk_context * ctx);
+void ggml_vk_cleanup(ggml_backend_vk_context * ctx);
+void ggml_vk_synchronize(ggml_backend_vk_context * ctx);
+bool ggml_vk_is_empty(ggml_tensor * node);
+bool ggml_vk_can_fuse(const ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx, std::initializer_list<enum ggml_op> ops);
+bool ggml_vk_can_fuse_ssm_conv(const ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx, int num_extra);
+bool ggml_vk_can_fuse_topk_moe(ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx, topk_moe_mode mode);
+bool ggml_vk_can_fuse_topk_qsa(ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx);
+bool ggml_vk_can_fuse_rope_set_rows(ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx);
+bool ggml_vk_can_fuse_rms_norm_set_rows(ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx);
+bool ggml_vk_can_fuse_snake(ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx);
+bool ggml_vk_tensors_overlap(const ggml_tensor * a, const ggml_tensor * b, bool elementwise);
+bool ggml_vk_can_fuse_rms_norm_mul_rope(ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx);
+uint32_t ggml_vk_fuse_multi_add(ggml_backend_vk_context * ctx, const struct ggml_cgraph * cgraph, int node_idx);
+void ggml_vk_graph_optimize(ggml_backend_t backend, struct ggml_cgraph * graph, struct ggml_backend_graph_optimize_params * params);
+
+// backend
+bool ggml_backend_buffer_is_vk(ggml_backend_buffer_t buffer);
+void ggml_backend_vk_buffer_free_buffer(ggml_backend_buffer_t buffer);
+void * ggml_backend_vk_buffer_get_base(ggml_backend_buffer_t buffer);
+enum ggml_status ggml_backend_vk_buffer_init_tensor(ggml_backend_buffer_t buffer, ggml_tensor * tensor);
+void ggml_backend_vk_buffer_memset_tensor(ggml_backend_buffer_t buffer, ggml_tensor * tensor, uint8_t value, size_t offset, size_t size);
+void ggml_backend_vk_buffer_set_tensor(ggml_backend_buffer_t buffer, ggml_tensor * tensor, const void * data, size_t offset, size_t size);
+void ggml_backend_vk_buffer_set_tensor_2d(ggml_backend_buffer_t buffer, ggml_tensor * tensor, const void * data, size_t offset, size_t size, size_t n_copies, size_t stride_tensor, size_t stride_data);
+void ggml_backend_vk_buffer_get_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * tensor, void * data, size_t offset, size_t size);
+void ggml_backend_vk_buffer_get_tensor_2d(ggml_backend_buffer_t buffer, const ggml_tensor * tensor, void * data, size_t offset, size_t size, size_t n_copies, size_t stride_tensor, size_t stride_data);
+bool ggml_backend_vk_buffer_cpy_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * src, ggml_tensor * dst);
+void ggml_backend_vk_buffer_clear(ggml_backend_buffer_t buffer, uint8_t value);
+const char * ggml_backend_vk_buffer_type_name(ggml_backend_buffer_type_t buft);
+ggml_backend_buffer_t ggml_backend_vk_buffer_type_alloc_buffer(ggml_backend_buffer_type_t buft, size_t size);
+size_t ggml_backend_vk_buffer_type_get_alignment(ggml_backend_buffer_type_t buft);
+size_t ggml_backend_vk_buffer_type_get_max_size(ggml_backend_buffer_type_t buft);
+size_t ggml_backend_vk_buffer_type_get_alloc_size(ggml_backend_buffer_type_t buft, const ggml_tensor * tensor);
+void ggml_backend_vk_free(ggml_backend_t backend);
+ggml_backend_reg_t ggml_backend_vk_reg();
+
+// debug
+int64_t ggml_vk_get_op_batch_size(const ggml_tensor * op);
+
+// ggml-vulkan.cpp (residual)
+bool ggml_vk_lightning_indexer_k_type_supported(ggml_type type);
+void ggml_vk_print_device_fault_info(const vk_device& device);
+uint64_t ggml_vk_get_node_flops(const ggml_tensor * node);
+void ggml_vk_print_node_list(const ggml_cgraph * cgraph, int start, int end);
+void ggml_vk_print_device_lost_info(const vk_device& device);
+size_t ggml_vk_tensor_buffer_offset(const ggml_backend_vk_context * ctx, const ggml_tensor * t);
+size_t ggml_vk_descriptor_offset(size_t tensor_offset, size_t alignment, size_t type_size);
+uint32_t ggml_vk_concat_unit_size(ggml_type type);
+bool ggml_vk_concat_supported(const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * dst);
+
+template <typename T>
+static void ggml_vk_dispatch_pipeline(ggml_backend_vk_context* ctx, vk_context& subctx, vk_pipeline& pipeline, std::initializer_list<vk::DescriptorBufferInfo> const& descriptor_buffer_infos, const T &push_constants, std::array<uint32_t, 3> elements) {
+    const uint32_t wg0 = CEIL_DIV(elements[0], pipeline->wg_denoms[0]);
+    const uint32_t wg1 = CEIL_DIV(elements[1], pipeline->wg_denoms[1]);
+    const uint32_t wg2 = CEIL_DIV(elements[2], pipeline->wg_denoms[2]);
+    VK_LOG_DEBUG("ggml_vk_dispatch_pipeline(" << pipeline->name << ", {";
+    for (auto& buffer : descriptor_buffer_infos) {
+        std::cerr << "(" << buffer.buffer << ", " << buffer.offset << ", " << buffer.range << "), ";
+    }
+    std::cerr << "}, (" << wg0 << "," << wg1 << "," << wg2 << "))");
+    GGML_ASSERT(wg0 <= ctx->device->properties.limits.maxComputeWorkGroupCount[0] &&
+                wg1 <= ctx->device->properties.limits.maxComputeWorkGroupCount[1] &&
+                wg2 <= ctx->device->properties.limits.maxComputeWorkGroupCount[2]);
+    GGML_ASSERT(ctx->descriptor_set_idx < ctx->descriptor_sets.size());
+    GGML_ASSERT(descriptor_buffer_infos.size() <= MAX_PARAMETER_COUNT);
+    GGML_ASSERT(pipeline->parameter_count == descriptor_buffer_infos.size());
+    GGML_ASSERT(pipeline->push_constant_size == push_constant_size(push_constants));
+
+    vk::DescriptorSet& descriptor_set = ctx->descriptor_sets[ctx->descriptor_set_idx++];
+    vk::WriteDescriptorSet write_descriptor_set{ descriptor_set, 0, 0, pipeline->parameter_count, vk::DescriptorType::eStorageBuffer, nullptr, descriptor_buffer_infos.begin() };
+    ctx->device->device.updateDescriptorSets({ write_descriptor_set }, {});
+
+    subctx->s->buffer->buf.pushConstants(pipeline->layout, vk::ShaderStageFlagBits::eCompute, 0, push_constant_size(push_constants), push_constant_data(push_constants));
+    subctx->s->buffer->buf.bindPipeline(vk::PipelineBindPoint::eCompute, pipeline->pipeline);
+    subctx->s->buffer->buf.bindDescriptorSets(vk::PipelineBindPoint::eCompute,
+                                pipeline->layout,
+                                0,
+                                { descriptor_set },
+                                {});
+    {
+        ggml_vk_debug_label dbg(subctx, pipeline->name, wg0, wg1, wg2);
+        subctx->s->buffer->buf.dispatch(wg0, wg1, wg2);
+    }
+}
+