![]() |
AI Engine-ML v2 Intrinsics User Guide
v2025.1
|
Elementwise matrix multiplications emulated on top of bfloat16. More...
Emulated vector float operations with dynamic negation of multiplication result, zeroing of acc1, negation of acc1 | |
| v16caccfloat | mul_elem_16_conf (v16cbfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v16caccfloat | negmul_elem_16_conf (v16cbfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v16caccfloat | mac_elem_16_conf (v16cbfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | msc_elem_16_conf (v16cbfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | addmac_elem_16_conf (v16cbfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | addmsc_elem_16_conf (v16cbfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | mul_elem_16_conf (v16cbfloat16 v1, v16bfloat16 v2, int sub_mask, int sub_mul) |
| v16caccfloat | negmul_elem_16_conf (v16cbfloat16 v1, v16bfloat16 v2, int sub_mask, int sub_mul) |
| v16caccfloat | mac_elem_16_conf (v16cbfloat16 v1, v16bfloat16 v2, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | msc_elem_16_conf (v16cbfloat16 v1, v16bfloat16 v2, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | addmac_elem_16_conf (v16cbfloat16 v1, v16bfloat16 v2, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | addmsc_elem_16_conf (v16cbfloat16 v1, v16bfloat16 v2, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | mul_elem_16_conf (v16bfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v16caccfloat | negmul_elem_16_conf (v16bfloat16 v1, v16cbfloat16 v2, int sub_mask, int sub_mul) |
| v16caccfloat | mac_elem_16_conf (v16bfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | msc_elem_16_conf (v16bfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | addmac_elem_16_conf (v16bfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | addmsc_elem_16_conf (v16bfloat16 v1, v16cbfloat16 v2, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | mul_elem_32_conf (v32cbfloat16 v1, v32cbfloat16 v2, int sub_mask, int sub_mul) |
| v32caccfloat | negmul_elem_32_conf (v32cbfloat16 v1, v32cbfloat16 v2, int sub_mask, int sub_mul) |
| v32caccfloat | mac_elem_32_conf (v32cbfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | msc_elem_32_conf (v32cbfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | addmac_elem_32_conf (v32cbfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | addmsc_elem_32_conf (v32cbfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | mul_elem_32_conf (v32cbfloat16 v1, v32bfloat16 v2, int sub_mask, int sub_mul) |
| v32caccfloat | negmul_elem_32_conf (v32cbfloat16 v1, v32bfloat16 v2, int sub_mask, int sub_mul) |
| v32caccfloat | mac_elem_32_conf (v32cbfloat16 v1, v32bfloat16 v2, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | msc_elem_32_conf (v32cbfloat16 v1, v32bfloat16 v2, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | addmac_elem_32_conf (v32cbfloat16 v1, v32bfloat16 v2, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | addmsc_elem_32_conf (v32cbfloat16 v1, v32bfloat16 v2, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | mul_elem_32_conf (v32bfloat16 v1, v32cbfloat16 v2, int sub_mask, int sub_mul) |
| v32caccfloat | negmul_elem_32_conf (v32bfloat16 v1, v32cbfloat16 v2, int sub_mask, int sub_mul) |
| v32caccfloat | mac_elem_32_conf (v32bfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | msc_elem_32_conf (v32bfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | addmac_elem_32_conf (v32bfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | addmsc_elem_32_conf (v32bfloat16 v1, v32cbfloat16 v2, v32caccfloat acc1, v32caccfloat 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 | |
| v16caccfloat | mul_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v16caccfloat | negmul_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v16caccfloat | mac_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | msc_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | addmac_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | addmsc_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | mul_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v16caccfloat | negmul_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v16caccfloat | mac_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | msc_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | addmac_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | addmsc_elem_16_conf (v16cbfloat16 v1, int sgn_x, v16bfloat16 v2, int sgn_y, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | mul_elem_16_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v16caccfloat | negmul_elem_16_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v16caccfloat | mac_elem_16_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | msc_elem_16_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v16caccfloat | addmac_elem_16_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v16caccfloat | addmsc_elem_16_conf (v16bfloat16 v1, int sgn_x, v16cbfloat16 v2, int sgn_y, v16caccfloat acc1, v16caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | mul_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v32caccfloat | negmul_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v32caccfloat | mac_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | msc_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | addmac_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | addmsc_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | mul_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32bfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v32caccfloat | negmul_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32bfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v32caccfloat | mac_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32bfloat16 v2, int sgn_y, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | msc_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32bfloat16 v2, int sgn_y, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | addmac_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32bfloat16 v2, int sgn_y, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | addmsc_elem_32_conf (v32cbfloat16 v1, int sgn_x, v32bfloat16 v2, int sgn_y, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | mul_elem_32_conf (v32bfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v32caccfloat | negmul_elem_32_conf (v32bfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, int sub_mask, int sub_mul) |
| v32caccfloat | mac_elem_32_conf (v32bfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | msc_elem_32_conf (v32bfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1) |
| v32caccfloat | addmac_elem_32_conf (v32bfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
| v32caccfloat | addmsc_elem_32_conf (v32bfloat16 v1, int sgn_x, v32cbfloat16 v2, int sgn_y, v32caccfloat acc1, v32caccfloat acc2, int zero_acc1, int sub_mask, int sub_mul, int sub_acc1, int sub_acc2) |
Elementwise matrix multiplications emulated on top of bfloat16.
| v16caccfloat addmac_elem_16 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 1 |
| v16caccfloat addmac_elem_16 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 1 |
| v16caccfloat addmac_elem_16 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 1 |
| v16caccfloat addmac_elem_16_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmac_elem_16_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmac_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmac_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmac_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmac_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v32caccfloat addmac_elem_32 | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 1 |
| v32caccfloat addmac_elem_32 | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 1 |
| v32caccfloat addmac_elem_32 | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| acc2 | Accumulator 1 |
| v32caccfloat addmac_elem_32_conf | ( | v32bfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmac_elem_32_conf | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmac_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32bfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmac_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmac_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmac_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v16caccfloat addmsc_elem_16 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat addmsc_elem_16 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat addmsc_elem_16 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat addmsc_elem_16_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmsc_elem_16_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmsc_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmsc_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmsc_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v16caccfloat addmsc_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1, | ||
| v16caccfloat | 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 |
| v32caccfloat addmsc_elem_32 | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat addmsc_elem_32 | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat addmsc_elem_32 | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | acc2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat addmsc_elem_32_conf | ( | v32bfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmsc_elem_32_conf | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmsc_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32bfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmsc_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmsc_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v32caccfloat addmsc_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1, | ||
| v32caccfloat | 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 |
| v16caccfloat mac_elem_16 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat mac_elem_16 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat mac_elem_16 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat mac_elem_16_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | 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 |
| v16caccfloat mac_elem_16_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | 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 |
| v16caccfloat mac_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | 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 |
| v16caccfloat mac_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | 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 |
| v16caccfloat mac_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | 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 |
| v16caccfloat mac_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | 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 |
| v32caccfloat mac_elem_32 | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat mac_elem_32 | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat mac_elem_32 | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat mac_elem_32_conf | ( | v32bfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | 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 |
| v32caccfloat mac_elem_32_conf | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | 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 |
| v32caccfloat mac_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32bfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | 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 |
| v32caccfloat mac_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | 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 |
| v32caccfloat mac_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | 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 |
| v32caccfloat mac_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | 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 |
| v16caccfloat msc_elem_16 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat msc_elem_16 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat msc_elem_16 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v16caccfloat msc_elem_16_conf | ( | v16bfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | 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 |
| v16caccfloat msc_elem_16_conf | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | 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 |
| v16caccfloat msc_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16bfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | 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 |
| v16caccfloat msc_elem_16_conf | ( | v16cbfloat16 | v1, |
| int | sgn_x, | ||
| v16cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v16caccfloat | 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 |
| v16caccfloat msc_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2, | ||
| v16caccfloat | 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 |
| v16caccfloat msc_elem_16_conf | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2, | ||
| v16caccfloat | 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 |
| v32caccfloat msc_elem_32 | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat msc_elem_32 | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat msc_elem_32 | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | acc1 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| acc1 | Accumulator 1 |
| v32caccfloat msc_elem_32_conf | ( | v32bfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | 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 |
| v32caccfloat msc_elem_32_conf | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | 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 |
| v32caccfloat msc_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32bfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | 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 |
| v32caccfloat msc_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | v2, | ||
| int | sgn_y, | ||
| v32caccfloat | 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 |
| v32caccfloat msc_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2, | ||
| v32caccfloat | 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 |
| v32caccfloat msc_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2, | ||
| v32caccfloat | 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 |
| v16caccfloat mul_elem_16 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v16caccfloat mul_elem_16 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v16caccfloat mul_elem_16 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v16caccfloat mul_elem_16_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 |
| v16caccfloat mul_elem_16_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 |
| v16caccfloat mul_elem_16_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 |
| v16caccfloat mul_elem_16_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 |
| v16caccfloat mul_elem_16_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 |
| v16caccfloat mul_elem_16_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 |
| v32caccfloat mul_elem_32 | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v32caccfloat mul_elem_32 | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v32caccfloat mul_elem_32 | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v32caccfloat mul_elem_32_conf | ( | v32bfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | 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 |
| v32caccfloat mul_elem_32_conf | ( | v32bfloat16 | v1, |
| v32cbfloat16 | 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 |
| v32caccfloat mul_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32bfloat16 | 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 |
| v32caccfloat mul_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | 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 |
| v32caccfloat mul_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32bfloat16 | 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 |
| v32caccfloat mul_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | 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 |
| v16caccfloat negmul_elem_16 | ( | v16bfloat16 | v1, |
| v16cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v16caccfloat negmul_elem_16 | ( | v16cbfloat16 | v1, |
| v16bfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v16caccfloat negmul_elem_16 | ( | v16cbfloat16 | v1, |
| v16cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v16caccfloat negmul_elem_16_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 |
| v16caccfloat negmul_elem_16_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 |
| v16caccfloat negmul_elem_16_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 |
| v16caccfloat negmul_elem_16_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 |
| v16caccfloat negmul_elem_16_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 |
| v16caccfloat negmul_elem_16_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 |
| v32caccfloat negmul_elem_32 | ( | v32bfloat16 | v1, |
| v32cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v32caccfloat negmul_elem_32 | ( | v32cbfloat16 | v1, |
| v32bfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v32caccfloat negmul_elem_32 | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | v2 ) |
| v1 | Matrix A |
| v2 | Matrix B |
| v32caccfloat negmul_elem_32_conf | ( | v32bfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | 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 |
| v32caccfloat negmul_elem_32_conf | ( | v32bfloat16 | v1, |
| v32cbfloat16 | 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 |
| v32caccfloat negmul_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32bfloat16 | 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 |
| v32caccfloat negmul_elem_32_conf | ( | v32cbfloat16 | v1, |
| int | sgn_x, | ||
| v32cbfloat16 | 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 |
| v32caccfloat negmul_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32bfloat16 | 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 |
| v32caccfloat negmul_elem_32_conf | ( | v32cbfloat16 | v1, |
| v32cbfloat16 | 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 |