L
查看中间代码
void slave_entire_6(void *argv)
{
int acc_cp_0_size;
int acc_cp_1_size;
acc_cp_0_size = 64 * 1 * 4;
acc_cp_1_size = 256;
acc_corenum = acc_get_num_threads();
acc_myid = acc_get_thread_num();
acc_check_ldm(0 + sizeof(_ldm_B) + sizeof(_ldm_i) + sizeof(_ldm_j) + sizeof(acc_data_ret) + sizeof(_ldm_A));
acc_ret = acc_sync_pe_m2l_nostride_copy(_ldm_A,A,acc_cp_0_size);
{
for (acc_blockindex_i0_0 = acc_myid * 1; acc_blockindex_i0_0 <= 127; acc_blockindex_i0_0 += 1 * acc_corenum) {
for (_ldm_i = 0; _ldm_i <= 0; _ldm_i += 1) {
for (_ldm_j = 0; _ldm_j <= 63; _ldm_j += 1) {
_ldm_B[_ldm_i][_ldm_j] = _ldm_A[_ldm_j] + (_ldm_i + acc_blockindex_i0_0);
}
}
_swacc_ret = acc_sync_pe_l2m_nostride_copy(&B[acc_blockindex_i0_0][0],_ldm_B[0],acc_cp_1_size);
}
}
}
注意 acc_ret = acc_sync_pe_m2l_nostride_copy(_ldm_A,A,acc_cp_0_size);
这就是完全拷贝 A
