matmul-analysis/BMM/BMM_Theory/examples/plans.csv

1	case_id	branch	npu	op	used_core_num	split_b	m_cnt	n_cnt	grid_k	core_map	b_core	merge_b0	single_core_m	single_core_n	single_core_k	k_l1	b_l1	l1_form	base_m	base_n	base_k	l2_policy_in	l2_policy_out	swizzle_w	workspace_bytes	tail_strategy	tail_m_cnt	tail_n_cnt	tail_k_cnt	tail_m_main	tail_n_main	tail_block_cnt	tail_wave_num	fixpipe_unitflag	out_dtype_bytes	note
2	to_matmul_demo	转Matmul	Ascend950PR	batch_mat_mul_v3	32	1	0	0	1	折叠为 Matmul [2048,2048]x[2048,2048], 复用 Matmul 切分体系	0	1	0	0	2048	0	1		0	0	0			0	0	转Matmul后由 Matmul 体系决定	1	1	1	0	0	0	0	True	2	BatchB=1免费折叠: 左矩阵 [1,2048,2048] 视图折叠为 [2048,2048], 零重排零 split
3	special_k0_demo	特殊分支	Ascend950PR	batch_mat_mul_v3	64	1	1	1	1	AIV 核间按行均分 (无 Cube tile 概念)	0	1	0	0	0	0	1	UB驻留(AIV)	0	0	0	allocate	direct_gm	0	0	不涉及(AIV逐元素)	1	1	1	0	0	0	0	False	2	K=0纯写值: 无任何计算, C=bias 或 0, 纯 AIV 写值; 按行均分到 AIV 核
4	special_k1_demo	特殊分支	Ascend950PR	batch_mat_mul_v3	64	1	1	1	1	AIV 核间按行均分 (无 Cube tile 概念)	0	1	0	0	1	0	1	UB驻留(AIV) UB乒乓	0	0	0	allocate	direct_gm	0	0	不涉及(AIV逐元素)	1	1	1	0	0	0	0	False	2	K=1逐元素乘: 退化为 C=A⊙B 无累加深度, Cube 16x16x16 粒度浪费 15/16; 走 AIV 通路 GM->UB->Mul->GM, UB乒乓 (B>=2*AIV 双batch乒乓流水)
5	merge_demo_k_trunc	MergeBatch	Ascend950PR	batch_mat_mul_v3	32	32	1	1	1	切B均分(核间零重复读零依赖)	64	4	128	128	256	256	8	合并驻留	128	128	128	allocate(GM->L1随路驻留L2)	direct_gm	0	0	不涉及(核内不切M/N)	1	1	1	0	0	0	0	True	2	b0=4 (L0C上限5.7/算存比上限19.0/b_core=64); K截断; 合并后单次DMA搬入 A'[128,256]+B'[256,128]
6	merge_iter_arbitrate	IterBatch	Ascend950PR	batch_mat_mul_v3	32	32	1	1	1	切B轮转分配(核间零重复读零依赖)	4	1	64	64	512	512	2	b_双batch乒乓	64	64	256	allocate(GM->L1随路驻留L2)	direct_gm(输出仅写一次,直写GM不占L2)	0	0	不涉及(核内不切M/N)	1	1	1	0	0	0	0	True	2	双batch乒乓: 2*(MK+KN)*dtype=256KB <= L1
7	iter_demo_form_b	IterBatch	Ascend950PR	batch_mat_mul_v3	32	32	1	1	1	切B轮转分配(核间零重复读零依赖)	4	1	64	64	256	256	2	b_双batch乒乓	64	64	256	allocate(GM->L1随路驻留L2)	direct_gm(输出仅写一次,直写GM不占L2)	0	0	不涉及(核内不切M/N)	1	1	1	0	0	0	0	True	2	双batch乒乓: 2*(MK+KN)*dtype=128KB <= L1
8	iter_demo_form_d	IterBatch	Ascend950PR	batch_mat_mul_v3	32	32	1	1	1	切B轮转分配(核间零重复读零依赖)	2	1	64	64	8192	1024	1	d_两侧都切K	64	64	256	allocate(GM->L1随路驻留L2)	direct_gm(输出仅写一次,直写GM不占L2)	0	0	不涉及(核内不切M/N)	1	1	1	0	0	0	0	True	2	两侧都切K: k_L1=1024, K段成对流水, batch边界天然无缝; dValueA=2048B/dValueB=128B
9	streamk_demo	StreamK	Ascend950PR	batch_mat_mul_v3	32	1	1	1	32	B/M/N切出4块, 每块32核切K归约 (归约组内核c负责K段[c*K/32,(c+1)*K/32))	1	1	128	128	320	256	1	K段标准分块流水	128	128	64	allocate(部分和驻留L2)	resident(部分和4B驻留L2, 防精度丢失不随C的fp16/fp8转换)	0	8388608	grid_K=32路切K+归约	1	1	32	0	0	0	0	True	4	P=1.00, grid_K=32, 部分和驻留L2按4B写出, AIV归约后按C dtype=2B写最终
10	asw_demo_full	ASW_Basic	Ascend950PR	batch_mat_mul_v3	32	1	47	47	1	B->M->N线性映射+ASW滑窗蛇形(W=4)	0	1	176	176	1024	256	1	双缓冲驻留当前tile输入	176	176	80	allocate(输入驻留L2吸收重复读)	direct_gm(输出直写GM不占L2)	4	0	方案B	52	52	1	52	52	2	139	True	2	L2场景B_输入驻留输出直写GM, r_in=1.00; 尾轮: 周长型主导, rho=0.06<rho_dv=0.53, A1b被dValue卡死, 方案B反超
11	asw_demo_reduce_core	ASW_Basic_降核	Ascend950PR	batch_mat_mul_v3	16	1	1	1	1	降核: 只用16核, 每核一个L0C满载输出块, 其余核闲置	0	1	256	256	128	128	1	标准核内流水	256	256	64	allocate	direct_gm	0	0	不涉及(每核一块无尾轮)	1	1	1	0	0	0	0	True	2	P=16.00<C, 降核是理性选择 (强切则 tile 跌破搬移效率下限反而更慢)