![]() |
AI Engine-ML Intrinsics User Guide (v2025.1)
|
Elementwise matrix multiplications emulated on top of bfloat16. More...
Elementwise matrix multiplications emulated on top of bfloat16.
Multiplication of (2x8) with (8x2) bfloat16 and complex bfloat16 | |
| v4caccfloat | mul_2x8_8x2 (v16bfloat16 a, v16cbfloat16 b) |
| v4caccfloat | negmul_2x8_8x2 (v16bfloat16 a, v16cbfloat16 b) |
| v4caccfloat | mac_2x8_8x2 (v16bfloat16 a, v16cbfloat16 b, v4caccfloat acc1) |
| v4caccfloat | msc_2x8_8x2 (v16bfloat16 a, v16cbfloat16 b, v4caccfloat acc1) |
| v4caccfloat | addmac_2x8_8x2 (v16bfloat16 a, v16cbfloat16 b, v4caccfloat acc1, v4caccfloat acc2) |
| v4caccfloat | addmsc_2x8_8x2 (v16bfloat16 a, v16cbfloat16 b, v4caccfloat acc1, v4caccfloat acc2) |
Multiplication of (2x8) with (8x2) complex bfloat16 and bfloat16 | |
| v4caccfloat | mul_2x8_8x2 (v16cbfloat16 a, v16bfloat16 b) |
| v4caccfloat | negmul_2x8_8x2 (v16cbfloat16 a, v16bfloat16 b) |
| v4caccfloat | mac_2x8_8x2 (v16cbfloat16 a, v16bfloat16 b, v4caccfloat acc1) |
| v4caccfloat | msc_2x8_8x2 (v16cbfloat16 a, v16bfloat16 b, v4caccfloat acc1) |
| v4caccfloat | addmac_2x8_8x2 (v16cbfloat16 a, v16bfloat16 b, v4caccfloat acc1, v4caccfloat acc2) |
| v4caccfloat | addmsc_2x8_8x2 (v16cbfloat16 a, v16bfloat16 b, v4caccfloat acc1, v4caccfloat acc2) |
Multiplication of (2x8) with (8x2) complex bfloat16 and complex bfloat16 | |
| v4caccfloat | mul_2x8_8x2 (v16cbfloat16 a, v16cbfloat16 b) |
| v4caccfloat | negmul_2x8_8x2 (v16cbfloat16 a, v16cbfloat16 b) |
| v4caccfloat | mac_2x8_8x2 (v16cbfloat16 a, v16cbfloat16 b, v4caccfloat acc1) |
| v4caccfloat | msc_2x8_8x2 (v16cbfloat16 a, v16cbfloat16 b, v4caccfloat acc1) |
| v4caccfloat | addmac_2x8_8x2 (v16cbfloat16 a, v16cbfloat16 b, v4caccfloat acc1, v4caccfloat acc2) |
| v4caccfloat | addmsc_2x8_8x2 (v16cbfloat16 a, v16cbfloat16 b, v4caccfloat acc1, v4caccfloat acc2) |
Multiplication of (2x8) with (8x2) bfloat16 and complex bfloat16 with dynamic negation of multiplication result | |
| v4caccfloat | mul_2x8_8x2_conf (v16bfloat16 a, v16cbfloat16 b, int sub_mul) |
| v4caccfloat | negmul_2x8_8x2_conf (v16bfloat16 a, v16cbfloat16 b, int sub_mul) |
Multiplication of (2x8) with (8x2) complex bfloat16 and bfloat16 with dynamic negation of multiplication result | |
| v4caccfloat | mul_2x8_8x2_conf (v16cbfloat16 a, v16bfloat16 b, int sub_mul) |
| v4caccfloat | negmul_2x8_8x2_conf (v16cbfloat16 a, v16bfloat16 b, int sub_mul) |
Multiplication of (2x8) with (8x2) complex bfloat16 and complex bfloat16 with dynamic negation of multiplication result | |
| v4caccfloat | mul_2x8_8x2_conf (v16cbfloat16 a, v16cbfloat16 b, int sub_mul) |
| v4caccfloat | negmul_2x8_8x2_conf (v16cbfloat16 a, v16cbfloat16 b, int sub_mul) |
Multiplication of (2x8) with (8x2) bfloat16 and complex bfloat16 with dynamic negation of multiplication result, zeroing of acc1, and negation of acc1 | |
| v4caccfloat | mac_2x8_8x2_conf (v16bfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v4caccfloat | msc_2x8_8x2_conf (v16bfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v4caccfloat | addmac_2x8_8x2_conf (v16bfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, v4caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v4caccfloat | addmsc_2x8_8x2_conf (v16bfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, v4caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
Multiplication of (2x8) with (8x2) complex bfloat16 and bfloat16 with dynamic negation of multiplication result, zeroing of acc1, and negation of acc1 | |
| v4caccfloat | mac_2x8_8x2_conf (v16cbfloat16 v1, v16bfloat16 v2, v4caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v4caccfloat | msc_2x8_8x2_conf (v16cbfloat16 v1, v16bfloat16 v2, v4caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v4caccfloat | addmac_2x8_8x2_conf (v16cbfloat16 v1, v16bfloat16 v2, v4caccfloat acc1, v4caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v4caccfloat | addmsc_2x8_8x2_conf (v16cbfloat16 v1, v16bfloat16 v2, v4caccfloat acc1, v4caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
Multiplication of (2x8) with (8x2) complex bfloat16 and complex bfloat16 with dynamic negation of multiplication result, zeroing of acc1, and negation of acc1 | |
| v4caccfloat | mac_2x8_8x2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v4caccfloat | msc_2x8_8x2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v4caccfloat | addmac_2x8_8x2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, v4caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v4caccfloat | addmsc_2x8_8x2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v4caccfloat acc1, v4caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
channel by channel multiplication of (1x2) with (2x1) complex bfloat16 and complex bfloat16 | |
| v8caccfloat | mul_elem_8_2 (v16cbfloat16 v1, v16cbfloat16 v2) |
| v8caccfloat | negmul_elem_8_2 (v16cbfloat16 v1, v16cbfloat16 v2) |
| v8caccfloat | mac_elem_8_2 (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1) |
| v8caccfloat | msc_elem_8_2 (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1) |
| v8caccfloat | addmac_elem_8_2 (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2) |
| v8caccfloat | addmsc_elem_8_2 (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2) |
channel by channel multiplication of (1x2) with (2x1) bfloat16 and complex bfloat16 | |
| v8caccfloat | mul_elem_8_2 (v16bfloat16 v1, v16cbfloat16 v2) |
| v8caccfloat | negmul_elem_8_2 (v16bfloat16 v1, v16cbfloat16 v2) |
| v8caccfloat | mac_elem_8_2 (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1) |
| v8caccfloat | msc_elem_8_2 (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1) |
| v8caccfloat | addmac_elem_8_2 (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2) |
| v8caccfloat | addmsc_elem_8_2 (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2) |
channel by channel multiplication of (1x2) with (2x1) complex bfloat16 and bfloat16 | |
| v8caccfloat | mul_elem_8_2 (v16cbfloat16 v1, v16bfloat16 v2) |
| v8caccfloat | negmul_elem_8_2 (v16cbfloat16 v1, v16bfloat16 v2) |
| v8caccfloat | mac_elem_8_2 (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1) |
| v8caccfloat | msc_elem_8_2 (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1) |
| v8caccfloat | addmac_elem_8_2 (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, v8caccfloat acc2) |
| v8caccfloat | addmsc_elem_8_2 (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, v8caccfloat acc2) |
channel by channel multiplication of (1x2) with (2x1) for complex bfloat16 and complex bfloat16 with dynamic negation of multiplication result | |
| v8caccfloat | mul_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, int sub_mul) |
channel by channel multiplication of (1x2) with (2x1) for complex bfloat16 and complex bfloat16 with dynamic negation of multiplication result, zeroing of acc1, and negation of acc1 | |
| v8caccfloat | mac_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | submac_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | submsc_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
channel by channel multiplication of (1x2) with (2x1) for complex cbfloat16 and bfloat16 with dynamic negation of multiplication result | |
| v8caccfloat | mul_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, int sub_mul) |
channel by channel multiplication of (1x2) with (2x1) for complex bfloat16 and bfloat16 with dynamic negation of multiplication result, zeroing of acc1, and negation of acc1 | |
| v8caccfloat | mac_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
channel by channel multiplication of (1x2) with (2x1) for bfloat16 and complex bfloat16 with dynamic negation of multiplication result | |
| v8caccfloat | mul_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, int sub_mul) |
channel by channel multiplication of (1x2) with (2x1) for bfloat16 and complex bfloat16 with dynamic negation of multiplication result, zeroing of acc1, and negation of acc1 | |
| v8caccfloat | mac_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mul, int sub_acc1, int sub_acc2) |
Emulated vector float operations with dynamic negation of multiplication result, zeroing of acc1, negation of acc1 | |
| v8caccfloat | mul_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v8caccfloat | mac_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16cbfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | mul_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, int sub_mask, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, int sub_mask, int sub_mul) |
| v8caccfloat | mac_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16cbfloat16 v1, v16bfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | mul_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v8caccfloat | mac_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16bfloat16 v1, v16cbfloat16 v2, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
Emulated vector float operations with dynamic sign, dynamic negation of multiplication result, zeroing of acc1, negation of acc1 | |
| v8caccfloat | mul_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v8caccfloat | mac_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | mul_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v8caccfloat | mac_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | mul_elem_8_2_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v8caccfloat | negmul_elem_8_2_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v8caccfloat | mac_elem_8_2_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | msc_elem_8_2_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v8caccfloat | addmac_elem_8_2_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v8caccfloat | addmsc_elem_8_2_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v8caccfloat acc1, v8caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v4caccfloat addmac_2x8_8x2 | ( | v16bfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v4caccfloat addmac_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16bfloat16 | b, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v4caccfloat addmac_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v4caccfloat addmac_2x8_8x2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v4caccfloat addmac_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v4caccfloat addmac_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v8caccfloat addmac_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v8caccfloat addmac_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v8caccfloat addmac_elem_8_2_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v4caccfloat addmsc_2x8_8x2 | ( | v16bfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v4caccfloat addmsc_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16bfloat16 | b, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v4caccfloat addmsc_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v4caccfloat addmsc_2x8_8x2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v4caccfloat addmsc_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v4caccfloat addmsc_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| v4caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v8caccfloat addmsc_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v8caccfloat addmsc_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 2 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat addmsc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v4caccfloat mac_2x8_8x2 | ( | v16bfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v4caccfloat mac_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16bfloat16 | b, | ||
| v4caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v4caccfloat mac_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v4caccfloat mac_2x8_8x2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v4caccfloat mac_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v4caccfloat mac_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat mac_elem_8_2 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v8caccfloat mac_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v8caccfloat mac_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v8caccfloat mac_elem_8_2_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat mac_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat mac_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat mac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat mac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat mac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat mac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| v4caccfloat msc_2x8_8x2 | ( | v16bfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v4caccfloat msc_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16bfloat16 | b, | ||
| v4caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v4caccfloat msc_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b, | ||
| v4caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v4caccfloat msc_2x8_8x2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v4caccfloat msc_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v4caccfloat msc_2x8_8x2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v4caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat msc_elem_8_2 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v8caccfloat msc_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v8caccfloat msc_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| v8caccfloat msc_elem_8_2_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat msc_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat msc_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat msc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat msc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat msc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat msc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat msc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mask, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| v8caccfloat msc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| v4caccfloat mul_2x8_8x2 | ( | v16bfloat16 | a, |
| v16cbfloat16 | b | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v4caccfloat mul_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16bfloat16 | b | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v4caccfloat mul_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v4caccfloat mul_2x8_8x2_conf | ( | v16bfloat16 | a, |
| v16cbfloat16 | b, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask for multiplication result |
| v4caccfloat mul_2x8_8x2_conf | ( | v16cbfloat16 | a, |
| v16bfloat16 | b, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask for multiplication result |
| v4caccfloat mul_2x8_8x2_conf | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask for multiplication result |
| v8caccfloat mul_elem_8_2 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v8caccfloat mul_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v8caccfloat mul_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v8caccfloat mul_elem_8_2_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat mul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask of multiplication result |
| v4caccfloat negmul_2x8_8x2 | ( | v16bfloat16 | a, |
| v16cbfloat16 | b | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v4caccfloat negmul_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16bfloat16 | b | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v4caccfloat negmul_2x8_8x2 | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v4caccfloat negmul_2x8_8x2_conf | ( | v16bfloat16 | a, |
| v16cbfloat16 | b, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask for multiplication result |
| v4caccfloat negmul_2x8_8x2_conf | ( | v16cbfloat16 | a, |
| v16bfloat16 | b, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask for multiplication result |
| v4caccfloat negmul_2x8_8x2_conf | ( | v16cbfloat16 | a, |
| v16cbfloat16 | b, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask for multiplication result |
| v8caccfloat negmul_elem_8_2 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v8caccfloat negmul_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v8caccfloat negmul_elem_8_2 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| v8caccfloat negmul_elem_8_2_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| sgn_x | Sign of input A |
| v2 | Matrix B |
| sgn_y | Sign of input B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mask, | ||
| int | sub_mul | ||
| ) |
| v1 | Matrix A |
| v2 | Matrix B |
| sub_mask | Complex negation mask of multiplication result |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat negmul_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| int | sub_mul | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| sub_mul | Negation mask of multiplication result |
| v8caccfloat submac_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |
| v8caccfloat submsc_elem_8_2_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v8caccfloat | acc1, | ||
| v8caccfloat | acc2, | ||
| int | zero_acc1, | ||
| int | sub_mul, | ||
| int | sub_acc1, | ||
| int | sub_acc2 | ||
| ) |
| a | Matrix A |
| b | Matrix B |
| acc1 | Accumulator 1 input |
| acc2 | Accumulator 2 input |
| zero_acc1 | Zeroing mask for acc1 |
| sub_mul | Negation mask of multiplication result |
| sub_acc1 | Negation mask of acc1 |
| sub_acc2 | Negation mask of acc2 |