clang format correction

src/cpu/aarch64/brgemm/jit_brgemm_kernel.cpp

@@ -770,7 +770,7 @@ void jit_brgemm_kernel_t::zero_accumulators(int bd_block2, bool is_bdb_tail,
     for_(int bd = 0; bd < bd_block; bd++)
     for (int ld = 0; ld < ld_block2; ld++) {
         auto zmm = accm(ld_block2, bd, ld);
-        // This part is moved here from apply_alpha_beta function so that fadd instruction can be avoided. 
+        // This part is moved here from apply_alpha_beta function so that fadd instruction can be avoided.
         // This is also required only when K is blocked.
         if (need_to_apply_beta && brg.K != brg.reduce_dim) {
             const bool is_tail = is_ld_tail && ld + 1 == ld_block2;

src/cpu/aarch64/matmul/brgemm_matmul_utils.cpp

@@ -629,10 +629,10 @@ float compute_blocking_heuristic_sve_256(brgemm_matmul_conf_t &bgmmc,
             }
         }
         min_m_blk = nstl::min(matmul.M, best_m_blk);
-        // Here min_m_blk is set based on M value and no.of threads. Decreasing m_blk size will 
-        // increase no.of m blocks which might make better utilisation of threads. But it is found 
-        // that m_blk being a factor of M is more important than max thread utilisation.Therefore 
-        // in scoring that has been given more weightage(0.7). This was experimentally verified to 
+        // Here min_m_blk is set based on M value and no.of threads. Decreasing m_blk size will
+        // increase no.of m blocks which might make better utilisation of threads. But it is found
+        // that m_blk being a factor of M is more important than max thread utilisation.Therefore
+        // in scoring that has been given more weightage(0.7). This was experimentally verified to
         // be the best hueristics with multiple shapes.
 
         bool low_spatial_work = matmul.M <= 40;