cpu: verbose: fix performance issues caused by using the thread pool

Author: sunxiaoxia2022

src/cpu/matmul/cpu_matmul_list.cpp

@@ -95,11 +95,11 @@ const impl_list_item_t impl_list[] = REG_MATMUL_P({
         CPU_INSTANCE_AVX512(brgemm_matmul_t,avx512_core)
         CPU_INSTANCE_AVX2(brgemm_matmul_t,avx2_vnni_2)
         CPU_INSTANCE_AVX2(brgemm_matmul_t,avx2_vnni)
+        CPU_INSTANCE_AVX2(brgemm_matmul_t, avx2)
         CPU_INSTANCE(gemm_f32_matmul_t)
         CPU_INSTANCE(gemm_bf16_matmul_t, f32)
         CPU_INSTANCE(gemm_bf16_matmul_t, bf16)
         CPU_INSTANCE(gemm_x8s8s32x_matmul_t)
-        CPU_INSTANCE_AVX2(brgemm_matmul_t, avx2)
         CPU_INSTANCE(ref_matmul_t)
         CPU_INSTANCE(ref_matmul_int8_t)
         // These implementations are enabled only when DNNL_EXPERIMENTAL_SPARSE

src/cpu/x64/jit_brgemm_conv_utils.cpp

@@ -2296,10 +2296,6 @@ status_t init_conf(jit_brgemm_conv_conf_t &jcp, cpu_isa_t isa,
 
     if (try_exec_type_res == false) return status::unimplemented;
 
-#if DNNL_CPU_THREADING_RUNTIME == DNNL_RUNTIME_THREADPOOL
-    adjust_nthr(jcp, src_d, dst_d);
-#endif
-
     // ============ end blocking ===========================================
     jcp.brg_type
             = (jcp.use_uker && one_of(jcp.exec_type, exec_base, exec_trans))
@@ -2530,10 +2526,6 @@ status_t init_1x1_conf(jit_brgemm_conv_conf_t &jcp, cpu_isa_t isa,
     }
     best_brgb.save_to_jcp(jcp);
 
-#if DNNL_CPU_THREADING_RUNTIME == DNNL_RUNTIME_THREADPOOL
-    adjust_nthr(jcp, src_d, dst_d);
-#endif
-
     // =============== end blocking =================================
 
     jcp.brg_stride_a = jcp.ic_block * jcp.src_dsz;