tests: add BF16 non-contig coverage for MUL_MAT permutations (#22689)

The MUL_MAT test loop iterates over base_types[] to generate non-contig
permutation cases (3 standard permutations across n in {1, 8, 16}).
BF16 is absent from base_types[], so these 9 cases were never generated
for BF16 even though every other type covered by base_types[] tests them.

Add the missing 9 cases explicitly: BF16 x F32, m=16, k=256, bs=[2,3],
permutations {0,2,1,3}, {0,1,3,2}, {0,3,2,1}, with n in {1, 8, 16}.

Suggested-by: @jeffbolznv

diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index c60f6d2c2b004d5dcd0fcffa3336512c8bd2ade7..8a561c038a186bc71b141fdb5bcf1810066a158b 100644 (file)
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -8337,6 +8337,18 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
             test_cases.emplace_back(new test_mul_mat(type_a, type_b, 16, 8, 256, {1536, 1}, {1, 1}));
         }
     }
+
+    // BF16 is absent from base_types: add the 3 standard non-contig permutations explicitly
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16,  1, 256, {2, 3}, {1, 1}, {0, 2, 1, 3}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16,  1, 256, {2, 3}, {1, 1}, {0, 1, 3, 2}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16,  1, 256, {2, 3}, {1, 1}, {0, 3, 2, 1}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16,  8, 256, {2, 3}, {1, 1}, {0, 2, 1, 3}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16,  8, 256, {2, 3}, {1, 1}, {0, 1, 3, 2}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16,  8, 256, {2, 3}, {1, 1}, {0, 3, 2, 1}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16, 16, 256, {2, 3}, {1, 1}, {0, 2, 1, 3}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16, 16, 256, {2, 3}, {1, 1}, {0, 1, 3, 2}));
+    test_cases.emplace_back(new test_mul_mat(GGML_TYPE_BF16, GGML_TYPE_F32, 16, 16, 256, {2, 3}, {1, 1}, {0, 3, 2, 1}));
+
     for (ggml_type type_a : other_types) {
         for (ggml_type type_b : {GGML_TYPE_F32}) {
             if (ggml_blck_size(type_a) != 256) {