Revive MUL_MAT_ID to perf testing

Author: rillomas

tests/test-backend-ops.cpp

@@ -7819,6 +7819,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
     for (int bs : {1, 4, 8, 32, 64, 128, 256, 512}) {
         for (ggml_type type_a : {GGML_TYPE_F32, GGML_TYPE_F16, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0, GGML_TYPE_Q4_K, GGML_TYPE_Q6_K, GGML_TYPE_IQ2_XS}) {
             for (ggml_type type_b : {GGML_TYPE_F32}) {
+                test_cases.emplace_back(new test_mul_mat_id(type_a, type_b, 128, 8, false, 768, bs, 2048));
                 test_cases.emplace_back(new test_mul_mat_id_fusion(type_a, type_b, 128, 8, false, 768, bs, 2048, 1));
             }
         }
@@ -7827,6 +7828,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
     for (int bs : {1, 4, 8, 32, 64, 128, 256, 512}) {
         for (ggml_type type_a : {GGML_TYPE_F32, GGML_TYPE_F16, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0, GGML_TYPE_Q4_K, GGML_TYPE_Q6_K, GGML_TYPE_IQ2_XS}) {
             for (ggml_type type_b : {GGML_TYPE_F32}) {
+                test_cases.emplace_back(new test_mul_mat_id(type_a, type_b, 32, 4, false, 1792, bs, 2048));
                 test_cases.emplace_back(new test_mul_mat_id_fusion(type_a, type_b, 32, 4, false, 1792, bs, 2048, 1));
             }
         }
@@ -7837,6 +7839,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
     for (int bs : {1, 4, 8, 512}) {
         for (ggml_type type_a : {GGML_TYPE_MXFP4}) {
             for (ggml_type type_b : {GGML_TYPE_F32}) {
+                test_cases.emplace_back(new test_mul_mat_id(type_a, type_b, 32, 4, false, 2880, bs, 2880));
                 test_cases.emplace_back(new test_mul_mat_id_fusion(type_a, type_b, 32, 4, false, 2880, bs, 2880, 1));
             }
         }