diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_annotated_ptr.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_annotated_ptr.cpp
index 21f101e000b52..aba9158454448 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_annotated_ptr.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_annotated_ptr.cpp
@@ -11,9 +11,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// Currently row major B fails when annotated_ptr is used
-// XFAIL: gpu
-
 #include "../common.hpp"
 
 #define SG_SZ 32
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_colmajorA_colmajorB.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_colmajorA_colmajorB.cpp
index aba19833ee581..498082ce0c4e7 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_colmajorA_colmajorB.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_colmajorA_colmajorB.cpp
@@ -14,8 +14,6 @@
 // This tests support of col major layout for matrix B which does transpose and
 // then VNNI transform. This is currently only available on AMX
 
-// XFAIL: gpu
-
 #include "../common.hpp"
 #include <iostream>
 #include <sycl/detail/core.hpp>
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_packedB.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_packedB.cpp
index 36346ba4a9f1a..c5ca75ad73af4 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_packedB.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_bfloat16_packedB.cpp
@@ -14,8 +14,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// XFAIL: gpu
-
 #include "../common.hpp"
 
 #define SG_SZ 32
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_colA_rowB_colC.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_colA_rowB_colC.cpp
index a10810bf4549c..eb9bdb14574ea 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_colA_rowB_colC.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_colA_rowB_colC.cpp
@@ -11,7 +11,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// XFAIL:*
 
 #include "../common.hpp"
 
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_colmajorA_colmajorB.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_colmajorA_colmajorB.cpp
index 177e4d6d861fa..a9f967b64d982 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_colmajorA_colmajorB.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_colmajorA_colmajorB.cpp
@@ -14,7 +14,6 @@
 // This tests support of col major layout for matrix B which does transpose and
 // then VNNI transform. This is currently only available on AMX
 
-// XFAIL: gpu
 
 #include "../common.hpp"
 
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_rowmajorA_rowmajorB.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_rowmajorA_rowmajorB.cpp
index d73a2300888d3..525351e35877f 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_rowmajorA_rowmajorB.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_int8_rowmajorA_rowmajorB.cpp
@@ -13,8 +13,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// XFAIL: gpu
-
 #include "../common.hpp"
 
 #define SG_SZ 32
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_out_bounds.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_out_bounds.cpp
index 3464677d17398..86305694399c5 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_out_bounds.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_out_bounds.cpp
@@ -13,8 +13,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// XFAIL:gpu
-
 #include "../common.hpp"
 
 #define SG_SZ 32
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_prefetch.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_prefetch.cpp
index a6ce09fe13b9f..f06ad24dab17c 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_prefetch.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_prefetch.cpp
@@ -10,8 +10,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// XFAIL: gpu
-
 // SG size = 32 is not currently supported for SYCL Joint Matrix by IGC on DG2
 // UNSUPPORTED: gpu-intel-dg2
 
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_rowmajorA_rowmajorB.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_rowmajorA_rowmajorB.cpp
index 0fe45a24c499f..d8eca6ea4d147 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_rowmajorA_rowmajorB.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_rowmajorA_rowmajorB.cpp
@@ -14,9 +14,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// Sub-group size 32 support for this test is not currently available in IGC
-// XFAIL: gpu
-
 #include "../common.hpp"
 
 using namespace sycl;
diff --git a/sycl/test-e2e/Matrix/SG32/joint_matrix_unaligned_k.cpp b/sycl/test-e2e/Matrix/SG32/joint_matrix_unaligned_k.cpp
index ceb196e07b9ca..e0f186470477f 100644
--- a/sycl/test-e2e/Matrix/SG32/joint_matrix_unaligned_k.cpp
+++ b/sycl/test-e2e/Matrix/SG32/joint_matrix_unaligned_k.cpp
@@ -13,8 +13,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// XFAIL:gpu
-
 #include "../common.hpp"
 
 #define SG_SZ 32
diff --git a/sycl/test-e2e/Matrix/joint_matrix_bfloat16_colmajorA_colmajorB.cpp b/sycl/test-e2e/Matrix/joint_matrix_bfloat16_colmajorA_colmajorB.cpp
index a9326e2ba312b..3be78a25f584c 100644
--- a/sycl/test-e2e/Matrix/joint_matrix_bfloat16_colmajorA_colmajorB.cpp
+++ b/sycl/test-e2e/Matrix/joint_matrix_bfloat16_colmajorA_colmajorB.cpp
@@ -13,7 +13,6 @@
 // This tests support of col major layout for matrix B which does transpose and
 // then VNNI transform. This is currently only available on AMX
 
-// XFAIL: gpu
 
 #include "common.hpp"
 
diff --git a/sycl/test-e2e/Matrix/joint_matrix_colA_rowB_colC.cpp b/sycl/test-e2e/Matrix/joint_matrix_colA_rowB_colC.cpp
index 71e3cb6501bb6..3b24e0be44d87 100644
--- a/sycl/test-e2e/Matrix/joint_matrix_colA_rowB_colC.cpp
+++ b/sycl/test-e2e/Matrix/joint_matrix_colA_rowB_colC.cpp
@@ -10,7 +10,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// XFAIL:*
 
 #include "common.hpp"
 
diff --git a/sycl/test-e2e/Matrix/joint_matrix_int8_colmajorA_colmajorB.cpp b/sycl/test-e2e/Matrix/joint_matrix_int8_colmajorA_colmajorB.cpp
index f8dc8452668a1..e8e3776e91811 100644
--- a/sycl/test-e2e/Matrix/joint_matrix_int8_colmajorA_colmajorB.cpp
+++ b/sycl/test-e2e/Matrix/joint_matrix_int8_colmajorA_colmajorB.cpp
@@ -13,8 +13,6 @@
 // This tests support of col major layout for matrix B which does transpose and
 // then VNNI transform. This is currently only available on AMX
 
-// XFAIL: gpu
-
 #include "common.hpp"
 
 constexpr size_t TN = 16;