VEXTRACTF64X4 (YMM, ZMM, I8) - Latency

Experiment 1

• Instruction: VEXTRACTF64X4 YMM1, ZMM0, 2
• Chain instructions: VANDPD YMM0, YMM1, YMM1;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0
• Chain latency: 5
• Code:

     0:	62 f3 fd 48 1b c1 02 	vextractf64x4 ymm1,zmm0,0x2
     7:	c5 f5 54 c1          	vandpd ymm0,ymm1,ymm1
     b:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
     f:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
    13:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
    17:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  VMOVUPD ZMM0, [R14]

• Show nanoBench command
• Results:
  • MPERF: 5.17
  • APERF: 6.04
  • UOPS: 6.0

Experiment 2

• Instruction: VEXTRACTF64X4 YMM1, ZMM0, 2
• Chain instructions: VPAND YMM0, YMM1, YMM1;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0
• Chain latency: 5
• Code:

     0:	62 f3 fd 48 1b c1 02 	vextractf64x4 ymm1,zmm0,0x2
     7:	c5 f5 db c1          	vpand  ymm0,ymm1,ymm1
     b:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
     f:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
    13:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
    17:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS ZMM0, ZMM1, ZMM1;
  VADDPS ZMM0, ZMM1, ZMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  VMOVUPD ZMM0, [R14]

• Show nanoBench command
• Results:
  • MPERF: 5.17
  • APERF: 6.0
  • UOPS: 6.0