1.3 KiB
1.3 KiB
| 1 | case_id | batch_a | batch_b | m | n | k | dtype_a | dtype_b | dtype_c | trans_a | trans_b | has_bias | out_nd | deterministic_level | plan_case_id | plan_branch | plan_npu | plan_op | plan_used_core_num | plan_split_b | plan_m_cnt | plan_n_cnt | plan_grid_k | plan_core_map | plan_b_core | plan_merge_b0 | plan_single_core_m | plan_single_core_n | plan_single_core_k | plan_k_l1 | plan_b_l1 | plan_l1_form | plan_base_m | plan_base_n | plan_base_k | plan_l2_policy_in | plan_l2_policy_out | plan_swizzle_w | plan_workspace_bytes | plan_tail_strategy | plan_tail_m_cnt | plan_tail_n_cnt | plan_tail_k_cnt | plan_tail_m_main | plan_tail_n_main | plan_tail_block_cnt | plan_tail_wave_num | plan_fixpipe_unitflag | plan_out_dtype_bytes | plan_note | gm_read_bytes | l2_read_bytes | t_mte2_gm | t_mte2_l2 | t_mte2 | dma_cmd_count | t_dma_cmd | cube_flops | t_mmad | fixpipe_bytes | t_fixpipe | t_reduce | t_steady | t_drain | t_total | bottleneck | feasible | violations | bound_type | advice |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | bug1 | 64 | 64 | 8192 | 32 | 1 | int8 | int8 | int8 | False | False | False | True | 0 | bug1 | 特殊分支 | Ascend950PR | batch_mat_mul_v3 | 0 | 1 | 1 | 1 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | True | 2 | 该区域暂无理论方案(进入条件不满足) | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | True | [无方案] K=1逐元素乘, 走AIV向量通路; 但进入条件不满足 (2_K=1的AIV触发: B >= 2*AIV核数 (开UB乒乓)), 该区域暂无理论方案, 建议参考 Cube 兜底或 AIV 单缓冲 |