diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16.cpp
index fb533762d91e4..2e26253f55984 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16.cpp
@@ -36,9 +36,13 @@ int main() {
   for (unsigned int i = 0; i < combinations.size(); i++) {
     if (combinations[i].nsize == 0) { // Intel AMX
       test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
-           layout::row_major, 1>();
-      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
            layout::ext_intel_packed, 2>();
+      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+           layout::ext_intel_packed, 2>();
+      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
+           layout::row_major, 1>();
+      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+           layout::row_major, 1>();
       break;
     }
 
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_half.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_half.cpp
index df1eecdd66c88..87a0a9856af61 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_half.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_half.cpp
@@ -35,9 +35,14 @@ int main() {
   for (unsigned int i = 0; i < combinations.size(); i++) {
     if (combinations[i].nsize == 0) { // Intel AMX
       test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
-           layout::row_major, 1>();
-      test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
            layout::ext_intel_packed, 2>();
+      test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+           layout::ext_intel_packed, 2>();
+      // VNNI transform does not work for half yet (CMPLRLLVM-69129)
+      //  test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
+      //       layout::row_major, 1>();
+      //  test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+      //       layout::row_major, 1>();
       break;
     }
 
diff --git a/sycl/test-e2e/Matrix/joint_matrix_bfloat16.cpp b/sycl/test-e2e/Matrix/joint_matrix_bfloat16.cpp
index 61afad345c511..fb69ade01f73f 100644
--- a/sycl/test-e2e/Matrix/joint_matrix_bfloat16.cpp
+++ b/sycl/test-e2e/Matrix/joint_matrix_bfloat16.cpp
@@ -29,9 +29,13 @@ int main() {
   for (unsigned int i = 0; i < combinations.size(); i++) {
     if (combinations[i].nsize == 0) { // Intel AMX
       test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
-           layout::row_major, 1>();
-      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
            layout::ext_intel_packed, 2>();
+      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+           layout::ext_intel_packed, 2>();
+      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
+           layout::row_major, 1>();
+      test<bfloat16, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+           layout::row_major, 1>();
       break;
     }
 
diff --git a/sycl/test-e2e/Matrix/joint_matrix_half.cpp b/sycl/test-e2e/Matrix/joint_matrix_half.cpp
index ab97297cbda1a..08f188b269f2f 100644
--- a/sycl/test-e2e/Matrix/joint_matrix_half.cpp
+++ b/sycl/test-e2e/Matrix/joint_matrix_half.cpp
@@ -26,9 +26,14 @@ int main() {
   for (unsigned int i = 0; i < combinations.size(); i++) {
     if (combinations[i].nsize == 0) { // Intel AMX
       test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
-           layout::row_major, 1>();
-      test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
            layout::ext_intel_packed, 2>();
+      test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+           layout::ext_intel_packed, 2>();
+      // VNNI transform does not work for half yet (CMPLRLLVM-69129)
+      //  test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 16,
+      //       layout::row_major, 1>();
+      //  test<half, float, float, /*TM*/ 16, /*TN*/ 16, /*TK*/ 32,
+      //       layout::row_major, 1>();
       break;
     }