@@ -524,47 +524,59 @@ v_cvt_pkrtz_f16_f32_e64_dpp v5, -v1, |v2| row_xmask:0 row_mask:0x1 bank_mask:0x3
524
524
v_cvt_pkrtz_f16_f32_e64_dpp v255, -|v255|, -|v255| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
525
525
// GFX11: v_cvt_pk_rtz_f16_f32_e64_dpp v255, -|v255|, -|v255| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x83,0x2f,0xd5,0xfa,0xfe,0x03,0x60,0xff,0x6f,0x05,0x30]
526
526
527
- v_fmac_f16_e64_dpp v5, v1, v2 quad_perm:[3 ,2 ,1 ,0 ]
528
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 quad_perm:[3 ,2 ,1 ,0 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
527
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l quad_perm:[3 ,2 ,1 ,0 ]
528
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l quad_perm:[3 ,2 ,1 ,0 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
529
529
530
- v_fmac_f16_e64_dpp v5, v1, v2 quad_perm:[0 ,1 ,2 ,3 ]
531
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 quad_perm:[0 ,1 ,2 ,3 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff]
530
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l quad_perm:[0 ,1 ,2 ,3 ]
531
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l quad_perm:[0 ,1 ,2 ,3 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0xe4,0x00,0xff]
532
532
533
- v_fmac_f16_e64_dpp v5, v1, v2 row_mirror
534
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff]
533
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_mirror
534
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x40,0x01,0xff]
535
535
536
- v_fmac_f16_e64_dpp v5, v1, v2 row_half_mirror
537
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff]
536
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_half_mirror
537
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x41,0x01,0xff]
538
538
539
- v_fmac_f16_e64_dpp v5, v1, v2 row_shl:1
540
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff]
539
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shl:1
540
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x01,0x01,0xff]
541
541
542
- v_fmac_f16_e64_dpp v5, v1, v2 row_shl:15
543
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff]
542
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shl:15
543
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x0f,0x01,0xff]
544
544
545
- v_fmac_f16_e64_dpp v5, v1, v2 row_shr:1
546
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff]
545
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shr:1
546
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x11,0x01,0xff]
547
547
548
- v_fmac_f16_e64_dpp v5, v1, v2 row_shr:15
549
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff]
548
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shr:15
549
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x1f,0x01,0xff]
550
550
551
- v_fmac_f16_e64_dpp v5, v1, v2 row_ror:1
552
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff]
551
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_ror:1
552
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x21,0x01,0xff]
553
553
554
- v_fmac_f16_e64_dpp v5, v1, v2 row_ror:15
555
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff]
554
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_ror:15
555
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_ror:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x2f,0x01,0xff]
556
556
557
- v_fmac_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf
558
- // GFX11: v_fmac_f16_e64_dpp v5, v1, v2 row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff]
557
+ v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_share:0 row_mask:0xf bank_mask:0xf
558
+ // GFX11: v_fmac_f16_e64_dpp v5.l , v1.l , v2.l row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff]
559
559
560
- v_fmac_f16_e64_dpp v5, |v1|, -v2 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
561
- // GFX11: v_fmac_f16_e64_dpp v5, |v1|, -v2 mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x36,0xd5,0xfa,0x04,0x02,0x48,0x01,0x5f,0x01,0x01]
560
+ v_fmac_f16_e64_dpp v5.l , |v1.l |, -v2.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
561
+ // GFX11: v_fmac_f16_e64_dpp v5.l , |v1.l |, -v2.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x01,0x36,0xd5,0xfa,0x04,0x02,0x48,0x01,0x5f,0x01,0x01]
562
562
563
- v_fmac_f16_e64_dpp v5, -v1, |v2| mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
564
- // GFX11: v_fmac_f16_e64_dpp v5, -v1, |v2| mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x02,0x36,0xd5,0xfa,0x04,0x02,0x30,0x01,0x60,0x09,0x13]
563
+ v_fmac_f16_e64_dpp v5.l , -v1.l , |v2.l | mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
564
+ // GFX11: v_fmac_f16_e64_dpp v5.l , -v1.l , |v2.l | mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x02,0x36,0xd5,0xfa,0x04,0x02,0x30,0x01,0x60,0x09,0x13]
565
565
566
- v_fmac_f16_e64_dpp v255, -|v255|, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
567
- // GFX11: v_fmac_f16_e64_dpp v255, -|v255|, -|v255| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x83,0x36,0xd5,0xfa,0xfe,0x03,0x78,0xff,0x6f,0x05,0x30]
566
+ v_fmac_f16_e64_dpp v255.l, -|v255.l|, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
567
+ // GFX11: v_fmac_f16_e64_dpp v255.l, -|v255.l|, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x83,0x36,0xd5,0xfa,0xfe,0x03,0x78,0xff,0x6f,0x05,0x30]
568
+
569
+ v_fmac_f16_e64_dpp v5.h, v1.h, v2.h row_share:0 row_mask:0xf bank_mask:0xf
570
+ // GFX11: v_fmac_f16_e64_dpp v5.h, v1.h, v2.h op_sel:[1 ,1 ,1 ,1 ] row_share:0 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x58,0x36,0xd5,0xfa,0x04,0x02,0x00,0x01,0x50,0x01,0xff]
571
+
572
+ v_fmac_f16_e64_dpp v5.l, |v1.h|, -v2.l mul:2 row_share:15 row_mask:0x0 bank_mask:0x1
573
+ // GFX11: v_fmac_f16_e64_dpp v5.l, |v1.h|, -v2.l op_sel:[1 ,0 ,0 ,0 ] mul:2 row_share:15 row_mask:0x0 bank_mask:0x1 ; encoding: [0x05,0x09,0x36,0xd5,0xfa,0x04,0x02,0x48,0x01,0x5f,0x01,0x01]
574
+
575
+ v_fmac_f16_e64_dpp v5.l, -v1.l, |v2.h| mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 fi:0
576
+ // GFX11: v_fmac_f16_e64_dpp v5.l, -v1.l, |v2.h| op_sel:[0 ,1 ,0 ,0 ] mul:4 row_xmask:0 row_mask:0x1 bank_mask:0x3 bound_ctrl:1 ; encoding: [0x05,0x12,0x36,0xd5,0xfa,0x04,0x02,0x30,0x01,0x60,0x09,0x13]
577
+
578
+ v_fmac_f16_e64_dpp v255.h, -|v255.l|, -|v255.l| clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
579
+ // GFX11: v_fmac_f16_e64_dpp v255.h, -|v255.l|, -|v255.l| op_sel:[0 ,0 ,1 ,1 ] clamp div:2 row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0xc3,0x36,0xd5,0xfa,0xfe,0x03,0x78,0xff,0x6f,0x05,0x30]
568
580
569
581
v_fmac_f32_e64_dpp v5, v1, v2 quad_perm:[3 ,2 ,1 ,0 ]
570
582
// GFX11: v_fmac_f32_e64_dpp v5, v1, v2 quad_perm:[3 ,2 ,1 ,0 ] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x2b,0xd5,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
0 commit comments