vulkan: Warptile tuning for Intel Xe2/Xe3 (#18178)

* modify warptile tuning for xe3

* intel vendor check w/ coopmat support

* fix back formatting

* fix formatting change 2

* move intel check to chip specific tuning part

* Change to support both windows and linux

* modify m_warptile to l_warptile for intel

* modify warptile tuning for bf16 matmuls to fix regression (m_warptile to l_warptile)

* Code style changes

* Code style changes (2)

* Code style changes (3)

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

@@ -2996,6 +2996,10 @@ 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_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 };
+            l_warptile_mmq = { 512, 128, 128, 32, subgroup_size_8, 32, 2, tm_m, tn_m, tk_m, subgroup_size_8 };
         }
 
         l_mmq_wg_denoms = l_wg_denoms = {128, 128, 1 };
@@ -3678,6 +3682,11 @@ static void ggml_vk_load_shaders(vk_device& device) {
         m_wg_denoms = { 64,  64, 1 };
         s_wg_denoms = { 32,  32, 1 };
 
+        if (device->vendor_id == VK_VENDOR_ID_INTEL && device->architecture == INTEL_XE2) {
+            // Xe2/Xe3 - bf16 warptile performance tuning
+            l_warptile = { 512, 128, 128, 16, subgroup_size_8, 32, 2, 4, 4, 1, subgroup_size_8 };
+        }
+
         CREATE_MM(GGML_TYPE_BF16, pipeline_matmul_bf16, matmul_bf16, , wg_denoms, warptile, vk_mat_mat_push_constants, 3, , 0);
         CREATE_MM(GGML_TYPE_BF16, pipeline_matmul_id_bf16, matmul_id_bf16, , wg_denoms, warptile, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);
     }
@@ -5061,11 +5070,23 @@ 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_m[i]    = true;
+                device->mul_mat_s[i]    = true;
+                device->mul_mat_id_l[i] = false;
+                device->mul_mat_id_m[i] = true;
+                device->mul_mat_id_s[i] = true;
+                break;
             case VK_VENDOR_ID_INTEL:
-                device->mul_mat_l[i] = false;
+                if (!device->coopmat_support || device->architecture != INTEL_XE2) {
+                    device->mul_mat_l[i] = false;
+                    device->mul_mat_id_l[i] = false;
+                } else {
+                    device->mul_mat_l[i] = true;  // if coopmat & XE2+, allow large matmul warptile config for Intel
+                    device->mul_mat_id_l[i] = true;
+                }
                 device->mul_mat_m[i] = true;
                 device->mul_mat_s[i] = true;
-                device->mul_mat_id_l[i] = false;
                 device->mul_mat_id_m[i] = true;
                 device->mul_mat_id_s[i] = true;
                 break;