VPCOMPRESSD (M512, K, ZMM)

Experiment 1

Instruction: VPCOMPRESSD zmmword ptr [R14] {K1}, ZMM0
Chain instructions: MOV R12, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12
Chain latency: ≥78

Code:

   0:	62 d2 7d 49 8b 06    	vpcompressd ZMMWORD PTR [r14]{k1},zmm0
   6:	4d 8b 26             	mov    r12,QWORD PTR [r14]
   9:	4d 63 e4             	movsxd r12,r12d
   c:	4d 63 e4             	movsxd r12,r12d
   f:	4d 63 e4             	movsxd r12,r12d
  12:	4d 63 e4             	movsxd r12,r12d
  15:	4d 63 e4             	movsxd r12,r12d
  18:	4d 63 e4             	movsxd r12,r12d
  1b:	4d 63 e4             	movsxd r12,r12d
  1e:	4d 63 e4             	movsxd r12,r12d
  21:	4d 63 e4             	movsxd r12,r12d
  24:	4d 63 e4             	movsxd r12,r12d
  27:	4d 63 e4             	movsxd r12,r12d
  2a:	4d 63 e4             	movsxd r12,r12d
  2d:	4d 63 e4             	movsxd r12,r12d
  30:	4d 63 e4             	movsxd r12,r12d
  33:	4d 63 e4             	movsxd r12,r12d
  36:	4d 63 e4             	movsxd r12,r12d
  39:	4d 63 e4             	movsxd r12,r12d
  3c:	4d 63 e4             	movsxd r12,r12d
  3f:	4d 63 e4             	movsxd r12,r12d
  42:	4d 63 e4             	movsxd r12,r12d
  45:	4d 63 e4             	movsxd r12,r12d
  48:	4d 63 e4             	movsxd r12,r12d
  4b:	4d 63 e4             	movsxd r12,r12d
  4e:	4d 63 e4             	movsxd r12,r12d
  51:	4d 63 e4             	movsxd r12,r12d
  54:	4d 63 e4             	movsxd r12,r12d
  57:	4d 63 e4             	movsxd r12,r12d
  5a:	4d 63 e4             	movsxd r12,r12d
  5d:	4d 63 e4             	movsxd r12,r12d
  60:	4d 63 e4             	movsxd r12,r12d
  63:	4d 63 e4             	movsxd r12,r12d
  66:	4d 63 e4             	movsxd r12,r12d
  69:	4d 63 e4             	movsxd r12,r12d
  6c:	4d 63 e4             	movsxd r12,r12d
  6f:	4d 63 e4             	movsxd r12,r12d
  72:	4d 63 e4             	movsxd r12,r12d
  75:	4d 63 e4             	movsxd r12,r12d
  78:	4d 63 e4             	movsxd r12,r12d
  7b:	4d 63 e4             	movsxd r12,r12d
  7e:	4d 63 e4             	movsxd r12,r12d
  81:	4d 63 e4             	movsxd r12,r12d
  84:	4d 63 e4             	movsxd r12,r12d
  87:	4d 63 e4             	movsxd r12,r12d
  8a:	4d 63 e4             	movsxd r12,r12d
  8d:	4d 63 e4             	movsxd r12,r12d
  90:	4d 63 e4             	movsxd r12,r12d
  93:	4d 63 e4             	movsxd r12,r12d
  96:	4d 63 e4             	movsxd r12,r12d
  99:	4d 63 e4             	movsxd r12,r12d
  9c:	4d 63 e4             	movsxd r12,r12d
  9f:	4d 63 e4             	movsxd r12,r12d
  a2:	4d 63 e4             	movsxd r12,r12d
  a5:	4d 63 e4             	movsxd r12,r12d
  a8:	4d 63 e4             	movsxd r12,r12d
  ab:	4d 63 e4             	movsxd r12,r12d
  ae:	4d 63 e4             	movsxd r12,r12d
  b1:	4d 63 e4             	movsxd r12,r12d
  b4:	4d 63 e4             	movsxd r12,r12d
  b7:	4d 63 e4             	movsxd r12,r12d
  ba:	4d 63 e4             	movsxd r12,r12d
  bd:	4d 63 e4             	movsxd r12,r12d
  c0:	4d 63 e4             	movsxd r12,r12d
  c3:	4d 63 e4             	movsxd r12,r12d
  c6:	4d 63 e4             	movsxd r12,r12d
  c9:	4d 63 e4             	movsxd r12,r12d
  cc:	4d 63 e4             	movsxd r12,r12d
  cf:	4d 63 e4             	movsxd r12,r12d
  d2:	4d 63 e4             	movsxd r12,r12d
  d5:	4d 63 e4             	movsxd r12,r12d
  d8:	4d 63 e4             	movsxd r12,r12d
  db:	4d 63 e4             	movsxd r12,r12d
  de:	4d 63 e4             	movsxd r12,r12d
  e1:	4d 63 e4             	movsxd r12,r12d
  e4:	4d 63 e4             	movsxd r12,r12d
  e7:	4d 63 e4             	movsxd r12,r12d
  ea:	4d 63 e4             	movsxd r12,r12d
  ed:	4d 31 e6             	xor    r14,r12
  f0:	4d 31 e6             	xor    r14,r12

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0

Show nanoBench command
Results:
- MPERF: 112.57
- APERF: 130.33
- UOPS: 223.0

Experiment 2 (with additional nop)

Instruction: VPCOMPRESSD zmmword ptr [R14] {K1}, ZMM0
Chain instructions: MOV R12, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12;nop
Chain latency: ≥78

Code:

   0:	62 d2 7d 49 8b 06    	vpcompressd ZMMWORD PTR [r14]{k1},zmm0
   6:	4d 8b 26             	mov    r12,QWORD PTR [r14]
   9:	4d 63 e4             	movsxd r12,r12d
   c:	4d 63 e4             	movsxd r12,r12d
   f:	4d 63 e4             	movsxd r12,r12d
  12:	4d 63 e4             	movsxd r12,r12d
  15:	4d 63 e4             	movsxd r12,r12d
  18:	4d 63 e4             	movsxd r12,r12d
  1b:	4d 63 e4             	movsxd r12,r12d
  1e:	4d 63 e4             	movsxd r12,r12d
  21:	4d 63 e4             	movsxd r12,r12d
  24:	4d 63 e4             	movsxd r12,r12d
  27:	4d 63 e4             	movsxd r12,r12d
  2a:	4d 63 e4             	movsxd r12,r12d
  2d:	4d 63 e4             	movsxd r12,r12d
  30:	4d 63 e4             	movsxd r12,r12d
  33:	4d 63 e4             	movsxd r12,r12d
  36:	4d 63 e4             	movsxd r12,r12d
  39:	4d 63 e4             	movsxd r12,r12d
  3c:	4d 63 e4             	movsxd r12,r12d
  3f:	4d 63 e4             	movsxd r12,r12d
  42:	4d 63 e4             	movsxd r12,r12d
  45:	4d 63 e4             	movsxd r12,r12d
  48:	4d 63 e4             	movsxd r12,r12d
  4b:	4d 63 e4             	movsxd r12,r12d
  4e:	4d 63 e4             	movsxd r12,r12d
  51:	4d 63 e4             	movsxd r12,r12d
  54:	4d 63 e4             	movsxd r12,r12d
  57:	4d 63 e4             	movsxd r12,r12d
  5a:	4d 63 e4             	movsxd r12,r12d
  5d:	4d 63 e4             	movsxd r12,r12d
  60:	4d 63 e4             	movsxd r12,r12d
  63:	4d 63 e4             	movsxd r12,r12d
  66:	4d 63 e4             	movsxd r12,r12d
  69:	4d 63 e4             	movsxd r12,r12d
  6c:	4d 63 e4             	movsxd r12,r12d
  6f:	4d 63 e4             	movsxd r12,r12d
  72:	4d 63 e4             	movsxd r12,r12d
  75:	4d 63 e4             	movsxd r12,r12d
  78:	4d 63 e4             	movsxd r12,r12d
  7b:	4d 63 e4             	movsxd r12,r12d
  7e:	4d 63 e4             	movsxd r12,r12d
  81:	4d 63 e4             	movsxd r12,r12d
  84:	4d 63 e4             	movsxd r12,r12d
  87:	4d 63 e4             	movsxd r12,r12d
  8a:	4d 63 e4             	movsxd r12,r12d
  8d:	4d 63 e4             	movsxd r12,r12d
  90:	4d 63 e4             	movsxd r12,r12d
  93:	4d 63 e4             	movsxd r12,r12d
  96:	4d 63 e4             	movsxd r12,r12d
  99:	4d 63 e4             	movsxd r12,r12d
  9c:	4d 63 e4             	movsxd r12,r12d
  9f:	4d 63 e4             	movsxd r12,r12d
  a2:	4d 63 e4             	movsxd r12,r12d
  a5:	4d 63 e4             	movsxd r12,r12d
  a8:	4d 63 e4             	movsxd r12,r12d
  ab:	4d 63 e4             	movsxd r12,r12d
  ae:	4d 63 e4             	movsxd r12,r12d
  b1:	4d 63 e4             	movsxd r12,r12d
  b4:	4d 63 e4             	movsxd r12,r12d
  b7:	4d 63 e4             	movsxd r12,r12d
  ba:	4d 63 e4             	movsxd r12,r12d
  bd:	4d 63 e4             	movsxd r12,r12d
  c0:	4d 63 e4             	movsxd r12,r12d
  c3:	4d 63 e4             	movsxd r12,r12d
  c6:	4d 63 e4             	movsxd r12,r12d
  c9:	4d 63 e4             	movsxd r12,r12d
  cc:	4d 63 e4             	movsxd r12,r12d
  cf:	4d 63 e4             	movsxd r12,r12d
  d2:	4d 63 e4             	movsxd r12,r12d
  d5:	4d 63 e4             	movsxd r12,r12d
  d8:	4d 63 e4             	movsxd r12,r12d
  db:	4d 63 e4             	movsxd r12,r12d
  de:	4d 63 e4             	movsxd r12,r12d
  e1:	4d 63 e4             	movsxd r12,r12d
  e4:	4d 63 e4             	movsxd r12,r12d
  e7:	4d 63 e4             	movsxd r12,r12d
  ea:	4d 63 e4             	movsxd r12,r12d
  ed:	4d 31 e6             	xor    r14,r12
  f0:	4d 31 e6             	xor    r14,r12
  f3:	90                   	nop

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0

Show nanoBench command
Results:
- MPERF: 112.49
- APERF: 130.3
- UOPS: 223.25

Latency operand 1 → 1 (address, index register): ≤51

Experiment 1

Instruction: VPCOMPRESSD zmmword ptr [R14+R13] {K1}, ZMM0
Chain instructions: MOV R12, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12
Chain latency: ≥78

Code:

   0:	62 92 7d 49 8b 04 2e 	vpcompressd ZMMWORD PTR [r14+r13*1]{k1},zmm0
   7:	4f 8b 24 2e          	mov    r12,QWORD PTR [r14+r13*1]
   b:	4d 63 e4             	movsxd r12,r12d
   e:	4d 63 e4             	movsxd r12,r12d
  11:	4d 63 e4             	movsxd r12,r12d
  14:	4d 63 e4             	movsxd r12,r12d
  17:	4d 63 e4             	movsxd r12,r12d
  1a:	4d 63 e4             	movsxd r12,r12d
  1d:	4d 63 e4             	movsxd r12,r12d
  20:	4d 63 e4             	movsxd r12,r12d
  23:	4d 63 e4             	movsxd r12,r12d
  26:	4d 63 e4             	movsxd r12,r12d
  29:	4d 63 e4             	movsxd r12,r12d
  2c:	4d 63 e4             	movsxd r12,r12d
  2f:	4d 63 e4             	movsxd r12,r12d
  32:	4d 63 e4             	movsxd r12,r12d
  35:	4d 63 e4             	movsxd r12,r12d
  38:	4d 63 e4             	movsxd r12,r12d
  3b:	4d 63 e4             	movsxd r12,r12d
  3e:	4d 63 e4             	movsxd r12,r12d
  41:	4d 63 e4             	movsxd r12,r12d
  44:	4d 63 e4             	movsxd r12,r12d
  47:	4d 63 e4             	movsxd r12,r12d
  4a:	4d 63 e4             	movsxd r12,r12d
  4d:	4d 63 e4             	movsxd r12,r12d
  50:	4d 63 e4             	movsxd r12,r12d
  53:	4d 63 e4             	movsxd r12,r12d
  56:	4d 63 e4             	movsxd r12,r12d
  59:	4d 63 e4             	movsxd r12,r12d
  5c:	4d 63 e4             	movsxd r12,r12d
  5f:	4d 63 e4             	movsxd r12,r12d
  62:	4d 63 e4             	movsxd r12,r12d
  65:	4d 63 e4             	movsxd r12,r12d
  68:	4d 63 e4             	movsxd r12,r12d
  6b:	4d 63 e4             	movsxd r12,r12d
  6e:	4d 63 e4             	movsxd r12,r12d
  71:	4d 63 e4             	movsxd r12,r12d
  74:	4d 63 e4             	movsxd r12,r12d
  77:	4d 63 e4             	movsxd r12,r12d
  7a:	4d 63 e4             	movsxd r12,r12d
  7d:	4d 63 e4             	movsxd r12,r12d
  80:	4d 63 e4             	movsxd r12,r12d
  83:	4d 63 e4             	movsxd r12,r12d
  86:	4d 63 e4             	movsxd r12,r12d
  89:	4d 63 e4             	movsxd r12,r12d
  8c:	4d 63 e4             	movsxd r12,r12d
  8f:	4d 63 e4             	movsxd r12,r12d
  92:	4d 63 e4             	movsxd r12,r12d
  95:	4d 63 e4             	movsxd r12,r12d
  98:	4d 63 e4             	movsxd r12,r12d
  9b:	4d 63 e4             	movsxd r12,r12d
  9e:	4d 63 e4             	movsxd r12,r12d
  a1:	4d 63 e4             	movsxd r12,r12d
  a4:	4d 63 e4             	movsxd r12,r12d
  a7:	4d 63 e4             	movsxd r12,r12d
  aa:	4d 63 e4             	movsxd r12,r12d
  ad:	4d 63 e4             	movsxd r12,r12d
  b0:	4d 63 e4             	movsxd r12,r12d
  b3:	4d 63 e4             	movsxd r12,r12d
  b6:	4d 63 e4             	movsxd r12,r12d
  b9:	4d 63 e4             	movsxd r12,r12d
  bc:	4d 63 e4             	movsxd r12,r12d
  bf:	4d 63 e4             	movsxd r12,r12d
  c2:	4d 63 e4             	movsxd r12,r12d
  c5:	4d 63 e4             	movsxd r12,r12d
  c8:	4d 63 e4             	movsxd r12,r12d
  cb:	4d 63 e4             	movsxd r12,r12d
  ce:	4d 63 e4             	movsxd r12,r12d
  d1:	4d 63 e4             	movsxd r12,r12d
  d4:	4d 63 e4             	movsxd r12,r12d
  d7:	4d 63 e4             	movsxd r12,r12d
  da:	4d 63 e4             	movsxd r12,r12d
  dd:	4d 63 e4             	movsxd r12,r12d
  e0:	4d 63 e4             	movsxd r12,r12d
  e3:	4d 63 e4             	movsxd r12,r12d
  e6:	4d 63 e4             	movsxd r12,r12d
  e9:	4d 63 e4             	movsxd r12,r12d
  ec:	4d 63 e4             	movsxd r12,r12d
  ef:	4d 31 e5             	xor    r13,r12
  f2:	4d 31 e5             	xor    r13,r12

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 111.47
- APERF: 129.34
- UOPS: 223.0

Experiment 2 (with additional nop)

Instruction: VPCOMPRESSD zmmword ptr [R14+R13] {K1}, ZMM0
Chain instructions: MOV R12, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12;nop
Chain latency: ≥78

Code:

   0:	62 92 7d 49 8b 04 2e 	vpcompressd ZMMWORD PTR [r14+r13*1]{k1},zmm0
   7:	4f 8b 24 2e          	mov    r12,QWORD PTR [r14+r13*1]
   b:	4d 63 e4             	movsxd r12,r12d
   e:	4d 63 e4             	movsxd r12,r12d
  11:	4d 63 e4             	movsxd r12,r12d
  14:	4d 63 e4             	movsxd r12,r12d
  17:	4d 63 e4             	movsxd r12,r12d
  1a:	4d 63 e4             	movsxd r12,r12d
  1d:	4d 63 e4             	movsxd r12,r12d
  20:	4d 63 e4             	movsxd r12,r12d
  23:	4d 63 e4             	movsxd r12,r12d
  26:	4d 63 e4             	movsxd r12,r12d
  29:	4d 63 e4             	movsxd r12,r12d
  2c:	4d 63 e4             	movsxd r12,r12d
  2f:	4d 63 e4             	movsxd r12,r12d
  32:	4d 63 e4             	movsxd r12,r12d
  35:	4d 63 e4             	movsxd r12,r12d
  38:	4d 63 e4             	movsxd r12,r12d
  3b:	4d 63 e4             	movsxd r12,r12d
  3e:	4d 63 e4             	movsxd r12,r12d
  41:	4d 63 e4             	movsxd r12,r12d
  44:	4d 63 e4             	movsxd r12,r12d
  47:	4d 63 e4             	movsxd r12,r12d
  4a:	4d 63 e4             	movsxd r12,r12d
  4d:	4d 63 e4             	movsxd r12,r12d
  50:	4d 63 e4             	movsxd r12,r12d
  53:	4d 63 e4             	movsxd r12,r12d
  56:	4d 63 e4             	movsxd r12,r12d
  59:	4d 63 e4             	movsxd r12,r12d
  5c:	4d 63 e4             	movsxd r12,r12d
  5f:	4d 63 e4             	movsxd r12,r12d
  62:	4d 63 e4             	movsxd r12,r12d
  65:	4d 63 e4             	movsxd r12,r12d
  68:	4d 63 e4             	movsxd r12,r12d
  6b:	4d 63 e4             	movsxd r12,r12d
  6e:	4d 63 e4             	movsxd r12,r12d
  71:	4d 63 e4             	movsxd r12,r12d
  74:	4d 63 e4             	movsxd r12,r12d
  77:	4d 63 e4             	movsxd r12,r12d
  7a:	4d 63 e4             	movsxd r12,r12d
  7d:	4d 63 e4             	movsxd r12,r12d
  80:	4d 63 e4             	movsxd r12,r12d
  83:	4d 63 e4             	movsxd r12,r12d
  86:	4d 63 e4             	movsxd r12,r12d
  89:	4d 63 e4             	movsxd r12,r12d
  8c:	4d 63 e4             	movsxd r12,r12d
  8f:	4d 63 e4             	movsxd r12,r12d
  92:	4d 63 e4             	movsxd r12,r12d
  95:	4d 63 e4             	movsxd r12,r12d
  98:	4d 63 e4             	movsxd r12,r12d
  9b:	4d 63 e4             	movsxd r12,r12d
  9e:	4d 63 e4             	movsxd r12,r12d
  a1:	4d 63 e4             	movsxd r12,r12d
  a4:	4d 63 e4             	movsxd r12,r12d
  a7:	4d 63 e4             	movsxd r12,r12d
  aa:	4d 63 e4             	movsxd r12,r12d
  ad:	4d 63 e4             	movsxd r12,r12d
  b0:	4d 63 e4             	movsxd r12,r12d
  b3:	4d 63 e4             	movsxd r12,r12d
  b6:	4d 63 e4             	movsxd r12,r12d
  b9:	4d 63 e4             	movsxd r12,r12d
  bc:	4d 63 e4             	movsxd r12,r12d
  bf:	4d 63 e4             	movsxd r12,r12d
  c2:	4d 63 e4             	movsxd r12,r12d
  c5:	4d 63 e4             	movsxd r12,r12d
  c8:	4d 63 e4             	movsxd r12,r12d
  cb:	4d 63 e4             	movsxd r12,r12d
  ce:	4d 63 e4             	movsxd r12,r12d
  d1:	4d 63 e4             	movsxd r12,r12d
  d4:	4d 63 e4             	movsxd r12,r12d
  d7:	4d 63 e4             	movsxd r12,r12d
  da:	4d 63 e4             	movsxd r12,r12d
  dd:	4d 63 e4             	movsxd r12,r12d
  e0:	4d 63 e4             	movsxd r12,r12d
  e3:	4d 63 e4             	movsxd r12,r12d
  e6:	4d 63 e4             	movsxd r12,r12d
  e9:	4d 63 e4             	movsxd r12,r12d
  ec:	4d 63 e4             	movsxd r12,r12d
  ef:	4d 31 e5             	xor    r13,r12
  f2:	4d 31 e5             	xor    r13,r12
  f5:	90                   	nop

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 111.47
- APERF: 129.34
- UOPS: 223.25

Latency operand 3 → 1: ≤40

Experiment 1

Instruction: VPCOMPRESSD zmmword ptr [R14] {K1}, ZMM0
Chain instructions: VMOVUPD XMM13, [R14];VANDPD XMM0, XMM13, XMM13;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0;VANDPD XMM0, XMM0, XMM0
Chain latency: ≥78

Code:

   0:	62 d2 7d 49 8b 06    	vpcompressd ZMMWORD PTR [r14]{k1},zmm0
   6:	c4 41 79 10 2e       	vmovupd xmm13,XMMWORD PTR [r14]
   b:	c4 c1 11 54 c5       	vandpd xmm0,xmm13,xmm13
  10:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  14:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  18:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  1c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  20:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  24:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  28:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  2c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  30:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  34:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  38:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  3c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  40:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  44:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  48:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  4c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  50:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  54:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  58:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  5c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  60:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  64:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  68:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  6c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  70:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  74:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  78:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  7c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  80:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  84:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  88:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  8c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  90:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  94:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  98:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  9c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  a0:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  a4:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  a8:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  ac:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  b0:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  b4:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  b8:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  bc:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  c0:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  c4:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  c8:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  cc:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  d0:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  d4:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  d8:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  dc:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  e0:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  e4:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  e8:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  ec:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  f0:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  f4:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  f8:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
  fc:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 100:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 104:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 108:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 10c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 110:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 114:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 118:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 11c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 120:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 124:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 128:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 12c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 130:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 134:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 138:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0
 13c:	c5 f9 54 c0          	vandpd xmm0,xmm0,xmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0

Show nanoBench command
Results:
- MPERF: 101.99
- APERF: 118.32
- UOPS: 222.0

Experiment 2

Instruction: VPCOMPRESSD zmmword ptr [R14] {K1}, ZMM0
Chain instructions: VMOVDQU XMM13, [R14];VPAND XMM0, XMM13, XMM13;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0;VPAND XMM0, XMM0, XMM0
Chain latency: ≥78

Code:

   0:	62 d2 7d 49 8b 06    	vpcompressd ZMMWORD PTR [r14]{k1},zmm0
   6:	c4 41 7a 6f 2e       	vmovdqu xmm13,XMMWORD PTR [r14]
   b:	c4 c1 11 db c5       	vpand  xmm0,xmm13,xmm13
  10:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  14:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  18:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  1c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  20:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  24:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  28:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  2c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  30:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  34:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  38:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  3c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  40:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  44:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  48:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  4c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  50:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  54:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  58:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  5c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  60:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  64:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  68:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  6c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  70:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  74:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  78:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  7c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  80:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  84:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  88:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  8c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  90:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  94:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  98:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  9c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  a0:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  a4:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  a8:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  ac:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  b0:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  b4:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  b8:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  bc:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  c0:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  c4:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  c8:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  cc:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  d0:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  d4:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  d8:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  dc:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  e0:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  e4:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  e8:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  ec:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  f0:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  f4:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  f8:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
  fc:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 100:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 104:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 108:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 10c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 110:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 114:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 118:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 11c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 120:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 124:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 128:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 12c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 130:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 134:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 138:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0
 13c:	c5 f9 db c0          	vpand  xmm0,xmm0,xmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0

Show nanoBench command
Results:
- MPERF: 101.99
- APERF: 118.36
- UOPS: 222.0

VPCOMPRESSD (M512, K, ZMM) - Latency

Operands

Latency operand 1 → 1 (address, base register): ≤52

Latency operand 1 → 1 (address, index register): ≤51

Latency operand 3 → 1: ≤40

Latency operand 1 → 1 (address, base register): ≤52

Experiment 1

Experiment 2 (with additional nop)

Latency operand 1 → 1 (address, index register): ≤51

Experiment 1

Experiment 2 (with additional nop)

Latency operand 3 → 1: ≤40

Experiment 1

Experiment 2