vulkan: add fast path for contiguous buffer transfers (#23973)

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

@@ -7615,9 +7615,13 @@ static void ggml_vk_buffer_write_2d(vk_buffer& dst, size_t offset, const void *
     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);
 
@@ -7735,9 +7739,13 @@ static void ggml_vk_buffer_read_2d(vk_buffer& src, size_t offset, void * dst, si
     if(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible && src->device->uma) {
         GGML_ASSERT(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostCoherent);
 
+        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);