/dports/math/blis/blis-0.8.1/kernels/knl/3/other/ |
H A D | bli_dgemm_knl_asm_12x16.c | 480 VGATHERDPD(ZMM(2) MASK_K(1), MEM(RCX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 481 VGATHERDPD(ZMM(3) MASK_K(2), MEM(RDX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 493 VGATHERDPD(ZMM(2) MASK_K(3), MEM(RCX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 494 VGATHERDPD(ZMM(3) MASK_K(4), MEM(RDX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 506 VGATHERDPD(ZMM(2) MASK_K(1), MEM(RCX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 507 VGATHERDPD(ZMM(3) MASK_K(2), MEM(RDX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 519 VGATHERDPD(ZMM(2) MASK_K(3), MEM(RCX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 520 VGATHERDPD(ZMM(3) MASK_K(4), MEM(RDX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 532 VGATHERDPD(ZMM(2) MASK_K(1), MEM(RCX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() 533 VGATHERDPD(ZMM(3) MASK_K(2), MEM(RDX,YMM(4),8)) in bli_dgemm_knl_asm_12x16() [all …]
|
H A D | bli_dgemm_knl_asm_8x24.c | 91 VGATHERDPD(ZMM(3) MASK_K(1), MEM(RCX,YMM(2),8)) \ 93 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(2), ZMM(NUM)) \ 100 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(1), ZMM(NUM)) \ 143 VGATHERPFDPS(0, MEM(RBX,ZMM(4),8,((3*n )*16+3*B_L1_PREFETCH_DIST)*64) MASK_K(1)) \ 145 VGATHERPFDPS(0, MEM(RBX,ZMM(4),8,((3*n+1)*16+3*B_L1_PREFETCH_DIST)*64) MASK_K(2)) \ 147 VGATHERPFDPS(0, MEM(RBX,ZMM(4),8,((3*n+2)*16+3*B_L1_PREFETCH_DIST)*64) MASK_K(3)) \ 149 VGATHERPFDPS(0, MEM(RAX,ZMM(4),8,( n *16+ A_L1_PREFETCH_DIST)*64) MASK_K(4)) 540 VSCATTERPFDPS(1, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_knl_asm_8x24() 541 VSCATTERPFDPD(1, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_dgemm_knl_asm_8x24() 579 VSCATTERPFDPS(0, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_knl_asm_8x24() [all …]
|
H A D | bli_dgemm_knl_asm_30x8.c | 103 VGATHERDPD(ZMM(1) MASK_K(1), MEM(RCX,YMM(0),8)) \ 105 VSCATTERDPD(MEM(RCX,YMM(0),8) MASK_K(2), ZMM(NUM)) \ 111 VSCATTERDPD(MEM(RCX,YMM(0),8) MASK_K(1), ZMM(NUM)) \ 271 VSCATTERPFDPS(1, MEM(RCX,ZMM(0),8) MASK_K(1)) in bli_dgemm_knl_asm_30x8() 272 VSCATTERPFDPS(1, MEM(RCX,ZMM(1),8) MASK_K(2)) in bli_dgemm_knl_asm_30x8() 472 VSCATTERPFDPS(0, MEM(RCX,ZMM(0),8) MASK_K(1)) in bli_dgemm_knl_asm_30x8() 473 VSCATTERPFDPS(0, MEM(RCX,ZMM(1),8) MASK_K(2)) in bli_dgemm_knl_asm_30x8()
|
/dports/math/tblis/tblis-1.2.0/src/configs/knl/ |
H A D | bli_dgemm_opt_12x16.c | 482 VGATHERDPD(ZMM(2) MASK_K(1), MEM(RCX,YMM(4),8)) in bli_dgemm_asm_12x16() 483 VGATHERDPD(ZMM(3) MASK_K(2), MEM(RDX,YMM(4),8)) in bli_dgemm_asm_12x16() 495 VGATHERDPD(ZMM(2) MASK_K(3), MEM(RCX,YMM(4),8)) in bli_dgemm_asm_12x16() 496 VGATHERDPD(ZMM(3) MASK_K(4), MEM(RDX,YMM(4),8)) in bli_dgemm_asm_12x16() 508 VGATHERDPD(ZMM(2) MASK_K(1), MEM(RCX,YMM(4),8)) in bli_dgemm_asm_12x16() 509 VGATHERDPD(ZMM(3) MASK_K(2), MEM(RDX,YMM(4),8)) in bli_dgemm_asm_12x16() 521 VGATHERDPD(ZMM(2) MASK_K(3), MEM(RCX,YMM(4),8)) in bli_dgemm_asm_12x16() 522 VGATHERDPD(ZMM(3) MASK_K(4), MEM(RDX,YMM(4),8)) in bli_dgemm_asm_12x16() 534 VGATHERDPD(ZMM(2) MASK_K(1), MEM(RCX,YMM(4),8)) in bli_dgemm_asm_12x16() 535 VGATHERDPD(ZMM(3) MASK_K(2), MEM(RDX,YMM(4),8)) in bli_dgemm_asm_12x16() [all …]
|
H A D | bli_sgemm_opt_24x16.c | 86 VGATHERDPS(ZMM(3) MASK_K(1), MEM(RCX,ZMM(2),4)) \ 88 VSCATTERDPS(MEM(RCX,ZMM(2),4) MASK_K(2), ZMM(NUM)) \ 95 VSCATTERDPS(MEM(RCX,ZMM(2),4) MASK_K(1), ZMM(NUM)) \ 268 VSCATTERPFDPS(1, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_sgemm_opt_24x16() 269 VSCATTERPFDPD(1, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_sgemm_opt_24x16() 451 VSCATTERPFDPS(0, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_sgemm_opt_24x16() 452 VSCATTERPFDPD(0, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_sgemm_opt_24x16()
|
H A D | bli_dgemm_opt_24x8.c | 86 VGATHERDPD(ZMM(3) MASK_K(1), MEM(RCX,YMM(2),8)) \ 88 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(2), ZMM(NUM)) \ 95 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(1), ZMM(NUM)) \ 271 VSCATTERPFDPS(1, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_opt_24x8() 272 VSCATTERPFDPD(1, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_dgemm_opt_24x8() 454 VSCATTERPFDPS(0, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_opt_24x8() 455 VSCATTERPFDPD(0, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_dgemm_opt_24x8()
|
H A D | bli_dgemm_opt_8x24.c | 86 VGATHERDPD(ZMM(3) MASK_K(1), MEM(RCX,YMM(2),8)) \ 88 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(2), ZMM(NUM)) \ 95 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(1), ZMM(NUM)) \ 271 VSCATTERPFDPS(1, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_opt_8x24() 272 VSCATTERPFDPD(1, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_dgemm_opt_8x24() 454 VSCATTERPFDPS(0, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_opt_8x24() 455 VSCATTERPFDPD(0, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_dgemm_opt_8x24()
|
H A D | bli_dgemm_opt_30x8.c | 103 VGATHERDPD(ZMM(1) MASK_K(1), MEM(RCX,YMM(0),8)) \ 105 VSCATTERDPD(MEM(RCX,YMM(0),8) MASK_K(2), ZMM(NUM)) \ 111 VSCATTERDPD(MEM(RCX,YMM(0),8) MASK_K(1), ZMM(NUM)) \ 272 VSCATTERPFDPS(1, MEM(RCX,ZMM(0),8) MASK_K(1)) in bli_dgemm_opt_30x8() 273 VSCATTERPFDPS(1, MEM(RCX,ZMM(1),8) MASK_K(2)) in bli_dgemm_opt_30x8() 473 VSCATTERPFDPS(0, MEM(RCX,ZMM(0),8) MASK_K(1)) in bli_dgemm_opt_30x8() 474 VSCATTERPFDPS(0, MEM(RCX,ZMM(1),8) MASK_K(2)) in bli_dgemm_opt_30x8()
|
H A D | bli_dpackm_opt_30x8.c | 382 VGATHERDPD(ZMM(4) MASK_K(1), MEM(RAX,YMM(0),8)) in bli_dpackm_30xk_opt() 383 VGATHERDPD(ZMM(5) MASK_K(2), MEM(RAX,YMM(1),8)) in bli_dpackm_30xk_opt() 384 VGATHERDPD(ZMM(6) MASK_K(3), MEM(RAX,YMM(2),8)) in bli_dpackm_30xk_opt() 385 VGATHERDPD(ZMM(7) MASK_K(4), MEM(RAX,YMM(3),8)) in bli_dpackm_30xk_opt()
|
H A D | bli_dpackm_opt_24x8.c | 264 VGATHERDPD(ZMM(3) MASK_K(1), MEM(RAX,YMM(0),8)) in bli_dpackm_8xk_opt() 503 VGATHERDPD(ZMM(3) MASK_K(1), MEM(RAX,YMM(0),8)) in bli_dpackm_24xk_opt() 504 VGATHERDPD(ZMM(4) MASK_K(2), MEM(RAX,YMM(1),8)) in bli_dpackm_24xk_opt() 505 VGATHERDPD(ZMM(5) MASK_K(3), MEM(RAX,YMM(2),8)) in bli_dpackm_24xk_opt()
|
/dports/math/blis/blis-0.8.1/kernels/skx/3/ |
H A D | bli_sgemm_skx_asm_32x12_l2.c | 96 VGATHERQPS(YMM(6) MASK_K(1), MEM(RCX,ZMM(2),1)) \ 97 VGATHERQPS(YMM(7) MASK_K(2), MEM(RCX,ZMM(3),1)) \ 100 VSCATTERQPS(MEM(RCX,ZMM(2),1) MASK_K(3), YMM(R1)) \ 101 VSCATTERQPS(MEM(RCX,ZMM(3),1) MASK_K(4), YMM( 5)) \ 109 VGATHERQPS(YMM(6) MASK_K(1), MEM(RDX,ZMM(2),1)) \ 110 VGATHERQPS(YMM(7) MASK_K(2), MEM(RDX,ZMM(3),1)) \ 113 VSCATTERQPS(MEM(RDX,ZMM(2),1) MASK_K(3), YMM(R2)) \ 125 VGATHERQPS(YMM(6) MASK_K(1), MEM(RCX,ZMM(2),1)) \ 126 VGATHERQPS(YMM(7) MASK_K(2), MEM(RCX,ZMM(3),1)) \ 138 VGATHERQPS(YMM(6) MASK_K(1), MEM(RDX,ZMM(2),1)) \ [all …]
|
H A D | bli_dgemm_skx_asm_16x12_l2.c | 102 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),1)) \ 104 VSCATTERQPD(MEM(RCX,ZMM(2),1) MASK_K(2), ZMM(R1)) \ 109 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),1)) \ 111 VSCATTERQPD(MEM(RCX,ZMM(3),1) MASK_K(2), ZMM(R2)) \ 118 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),1)) \ 120 VSCATTERQPD(MEM(RCX,ZMM(2),1) MASK_K(2), ZMM(R3)) \ 125 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),1)) \ 127 VSCATTERQPD(MEM(RCX,ZMM(3),1) MASK_K(2), ZMM(R4)) \ 135 VSCATTERQPD(MEM(RCX,ZMM(2),1) MASK_K(1), ZMM(R1)) \ 139 VSCATTERQPD(MEM(RCX,ZMM(3),1) MASK_K(1), ZMM(R2)) \ [all …]
|
H A D | bli_dgemm_skx_asm_16x14.c | 74 VGATHERQPD(ZMM(0) MASK_K(1), MEM(RCX,ZMM(2),1)) \ 76 VGATHERQPD(ZMM(0) MASK_K(2), MEM(RCX,ZMM(3),1)) \ 78 VSCATTERQPD(MEM(RCX,ZMM(2),1) MASK_K(3), ZMM(R1)) \ 79 VSCATTERQPD(MEM(RCX,ZMM(3),1) MASK_K(4), ZMM(R2)) \ 86 VSCATTERQPD(MEM(RCX,ZMM(2),1) MASK_K(1), ZMM(R1)) \ 87 VSCATTERQPD(MEM(RCX,ZMM(3),1) MASK_K(2), ZMM(R2)) \
|
/dports/math/tblis/tblis-1.2.0/src/configs/skx2/ |
H A D | bli_dgemm_opt_8x8_l1.c | 77 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 79 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 86 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 88 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R2)) \ 95 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 97 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R3)) \ 104 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 106 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R4)) \ 114 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 120 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R2)) \ [all …]
|
H A D | bli_dgemm_opt_8x8_l2.c | 82 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 84 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 91 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 93 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R2)) \ 100 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 102 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R3)) \ 109 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 111 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R4)) \ 119 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 125 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R2)) \ [all …]
|
H A D | bli_dgemm_opt_6x32_l1.c | 77 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 79 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 84 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 86 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R2)) \ 91 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(4),8)) \ 93 VSCATTERQPD(MEM(RCX,ZMM(4),8) MASK_K(2), ZMM(R3)) \ 98 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(5),8)) \ 100 VSCATTERQPD(MEM(RCX,ZMM(5),8) MASK_K(2), ZMM(R4)) \ 108 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 112 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(1), ZMM(R2)) \ [all …]
|
H A D | bli_dgemm_opt_12x16_l1.c | 77 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 79 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 84 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 86 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R2)) \ 93 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 95 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R3)) \ 100 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 102 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R4)) \ 110 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 114 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(1), ZMM(R2)) \ [all …]
|
H A D | bli_dgemm_opt_6x32_l2.c | 84 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 86 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 91 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 93 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R2)) \ 98 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(4),8)) \ 100 VSCATTERQPD(MEM(RCX,ZMM(4),8) MASK_K(2), ZMM(R3)) \ 105 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(5),8)) \ 107 VSCATTERQPD(MEM(RCX,ZMM(5),8) MASK_K(2), ZMM(R4)) \ 115 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 119 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(1), ZMM(R2)) \ [all …]
|
H A D | bli_dgemm_opt_12x16_l2.c | 94 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 96 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 101 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 103 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R2)) \ 110 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 112 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R3)) \ 117 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 119 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R4)) \ 127 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 131 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(1), ZMM(R2)) \ [all …]
|
H A D | bli_dgemm_opt_8x24_l1.c | 72 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 74 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 79 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 81 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R2)) \ 86 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(4),8)) \ 88 VSCATTERQPD(MEM(RCX,ZMM(4),8) MASK_K(2), ZMM(R3)) \ 96 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 100 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(1), ZMM(R2)) \ 104 VSCATTERQPD(MEM(RCX,ZMM(4),8) MASK_K(1), ZMM(R3)) \
|
H A D | bli_dgemm_opt_8x24_l2.c | 79 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(2),8)) \ 81 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(2), ZMM(R1)) \ 86 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(3),8)) \ 88 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(2), ZMM(R2)) \ 93 VGATHERQPD(ZMM(6) MASK_K(1), MEM(RCX,ZMM(4),8)) \ 95 VSCATTERQPD(MEM(RCX,ZMM(4),8) MASK_K(2), ZMM(R3)) \ 103 VSCATTERQPD(MEM(RCX,ZMM(2),8) MASK_K(1), ZMM(R1)) \ 107 VSCATTERQPD(MEM(RCX,ZMM(3),8) MASK_K(1), ZMM(R2)) \ 111 VSCATTERQPD(MEM(RCX,ZMM(4),8) MASK_K(1), ZMM(R3)) \
|
H A D | bli_sgemm_opt_12x32_l2.c | 86 VSCATTERQPS(MEM(C,ZMM(2),1) MASK_K(1), YMM(4)) \ 87 VSCATTERQPS(MEM(C,ZMM(3),1) MASK_K(2), YMM(5)) 98 VGATHERQPS(YMM(6) MASK_K(1), MEM(C,ZMM(2),1)) \ 99 VGATHERQPS(YMM(7) MASK_K(2), MEM(C,ZMM(3),1)) \ 102 VSCATTERQPS(MEM(C,ZMM(2),1) MASK_K(3), YMM(4)) \ 103 VSCATTERQPS(MEM(C,ZMM(3),1) MASK_K(4), YMM(5))
|
/dports/math/blis/blis-0.8.1/kernels/knl/3/ |
H A D | bli_sgemm_knl_asm_24x16.c | 87 VGATHERDPS(ZMM(3) MASK_K(1), MEM(RCX,ZMM(2),4)) \ 89 VSCATTERDPS(MEM(RCX,ZMM(2),4) MASK_K(2), ZMM(NUM)) \ 96 VSCATTERDPS(MEM(RCX,ZMM(2),4) MASK_K(1), ZMM(NUM)) \ 270 VSCATTERPFDPS(1, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_sgemm_knl_asm_24x16() 271 VSCATTERPFDPD(1, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_sgemm_knl_asm_24x16() 453 VSCATTERPFDPS(0, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_sgemm_knl_asm_24x16() 454 VSCATTERPFDPD(0, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_sgemm_knl_asm_24x16()
|
H A D | bli_dgemm_knl_asm_24x8.c | 87 VGATHERDPD(ZMM(3) MASK_K(1), MEM(RCX,YMM(2),8)) \ 89 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(2), ZMM(NUM)) \ 96 VSCATTERDPD(MEM(RCX,YMM(2),8) MASK_K(1), ZMM(NUM)) \ 273 VSCATTERPFDPS(1, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_knl_asm_24x8() 274 VSCATTERPFDPD(1, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_dgemm_knl_asm_24x8() 456 VSCATTERPFDPS(0, MEM(RCX,ZMM(2),8) MASK_K(1)) in bli_dgemm_knl_asm_24x8() 457 VSCATTERPFDPD(0, MEM(RCX,YMM(3),8) MASK_K(2)) in bli_dgemm_knl_asm_24x8()
|
/dports/math/blis/blis-0.8.1/kernels/knl/1m/old/ |
H A D | bli_packm_knl_asm_30x8.c | 381 VGATHERDPD(ZMM(4) MASK_K(1), MEM(RAX,YMM(0),8)) in bli_dpackm_knl_asm_30xk() 382 VGATHERDPD(ZMM(5) MASK_K(2), MEM(RAX,YMM(1),8)) in bli_dpackm_knl_asm_30xk() 383 VGATHERDPD(ZMM(6) MASK_K(3), MEM(RAX,YMM(2),8)) in bli_dpackm_knl_asm_30xk() 384 VGATHERDPD(ZMM(7) MASK_K(4), MEM(RAX,YMM(3),8)) in bli_dpackm_knl_asm_30xk()
|