[SYCL][E2E] Remove xfail from Joint Matrix prefetch tests

Author: dkhaldi

sycl/test-e2e/Matrix/SPVCooperativeMatrix/joint_matrix_prefetch.cpp

@@ -10,8 +10,6 @@
 // RUN: %{run} %t.out
 
 // XFAIL: cpu
-// https://github.com/intel/llvm/issues/14826
-// XFAIL: arch-intel_gpu_pvc && !igc-dev
 
 #include "../common.hpp"
 

sycl/test-e2e/Matrix/joint_matrix_bf16_fill_k_cache_prefetch.cpp

@@ -16,11 +16,5 @@
 
 // -ffp-model=precise is added to not depend on compiler defaults.
 
-// This test will be adjusted to run on the CPU
-// XFAIL:cpu
-
-// https://github.com/intel/llvm/issues/14826
-// XFAIL: arch-intel_gpu_pvc && !igc-dev
-
 #include "common.hpp"
 #include "joint_matrix_bf16_fill_k_cache_impl.hpp"

sycl/test-e2e/Matrix/joint_matrix_prefetch.cpp

@@ -9,9 +9,6 @@
 // RUN: %{build} -o %t.out
 // RUN: %{run} %t.out
 
-// https://github.com/intel/llvm/issues/14826
-// XFAIL: arch-intel_gpu_pvc && !igc-dev
-
 #include "common.hpp"
 
 constexpr size_t TN = 16;