Vulkan: Optimize Matmul parameters for AMD GPUs with Coopmat support (llama/18749)

* vulkan: Enable and optimize large matmul parameter combination for AMD

* limit tuning to AMD GPUs with coopmat support

* use tx_m values instead of _l

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index b1a51a43658f70a7c2c4c59c46115118b9bcde29..0d658575322ad13b6fcf9b9e424b7ac4378e37fe 100644 (file)
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -3002,6 +3002,11 @@ static void ggml_vk_load_shaders(vk_device& device) {
         if ((device->architecture == AMD_GCN) && (device->driver_id != vk::DriverId::eAmdProprietary)) {
             m_warptile_mmq = m_warptile_mmq_int = { 256, 64, 64, 32, 16, 16, 2, 2, 2, 1, 16 };
             m_warptile_mmqid = m_warptile_mmqid_int = { 256, 64, 64, 32, 16, 16, 2, 2, 2, 1, 16 };
+        } else if (device->vendor_id == VK_VENDOR_ID_AMD && device->coopmat_support) {
+            // This is intentionally using tx_m values, slight performance increase
+            l_warptile = { 256, 128, 128, 16, subgroup_size_8, 64, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
+            l_warptile_mmq = l_warptile_mmq_int = { 256, 128, 128, 32, subgroup_size_8, 64, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
+            l_warptile_mmq_int_k = { 256, 128, 128, 32, subgroup_size_16, 64, 1, 4, 2, 1, subgroup_size_16 };
         } else if (device->vendor_id == VK_VENDOR_ID_INTEL && device->coopmat_support && device->architecture == INTEL_XE2) {
             // Xe2/Xe3 with coopmat enabled - warptile performance tuning
             l_warptile = { 512, 128, 128, 16, subgroup_size_8, 32, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
@@ -5078,7 +5083,7 @@ static vk_device ggml_vk_get_device(size_t idx) {
             switch (device->vendor_id) {
 #ifndef GGML_VULKAN_RUN_TESTS
             case VK_VENDOR_ID_AMD:
-                device->mul_mat_l[i]    = false;
+                device->mul_mat_l[i]    = device->coopmat_support;
                 device->mul_mat_m[i]    = true;
                 device->mul_mat_s[i]    = true;
                 device->mul_mat_id_l[i] = false;