PDEP (R64, R64, M64)

Experiment 1

Instruction: PDEP R9, R8, qword ptr [R14]
Chain instructions: MOVSX R8, R9D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
Chain latency: 63

Code:

   0:	c4 42 bb f5 0e       	pdep   r9,r8,QWORD PTR [r14]
   5:	4d 63 c1             	movsxd r8,r9d
   8:	4d 63 c0             	movsxd r8,r8d
   b:	4d 63 c0             	movsxd r8,r8d
   e:	4d 63 c0             	movsxd r8,r8d
  11:	4d 63 c0             	movsxd r8,r8d
  14:	4d 63 c0             	movsxd r8,r8d
  17:	4d 63 c0             	movsxd r8,r8d
  1a:	4d 63 c0             	movsxd r8,r8d
  1d:	4d 63 c0             	movsxd r8,r8d
  20:	4d 63 c0             	movsxd r8,r8d
  23:	4d 63 c0             	movsxd r8,r8d
  26:	4d 63 c0             	movsxd r8,r8d
  29:	4d 63 c0             	movsxd r8,r8d
  2c:	4d 63 c0             	movsxd r8,r8d
  2f:	4d 63 c0             	movsxd r8,r8d
  32:	4d 63 c0             	movsxd r8,r8d
  35:	4d 63 c0             	movsxd r8,r8d
  38:	4d 63 c0             	movsxd r8,r8d
  3b:	4d 63 c0             	movsxd r8,r8d
  3e:	4d 63 c0             	movsxd r8,r8d
  41:	4d 63 c0             	movsxd r8,r8d
  44:	4d 63 c0             	movsxd r8,r8d
  47:	4d 63 c0             	movsxd r8,r8d
  4a:	4d 63 c0             	movsxd r8,r8d
  4d:	4d 63 c0             	movsxd r8,r8d
  50:	4d 63 c0             	movsxd r8,r8d
  53:	4d 63 c0             	movsxd r8,r8d
  56:	4d 63 c0             	movsxd r8,r8d
  59:	4d 63 c0             	movsxd r8,r8d
  5c:	4d 63 c0             	movsxd r8,r8d
  5f:	4d 63 c0             	movsxd r8,r8d
  62:	4d 63 c0             	movsxd r8,r8d
  65:	4d 63 c0             	movsxd r8,r8d
  68:	4d 63 c0             	movsxd r8,r8d
  6b:	4d 63 c0             	movsxd r8,r8d
  6e:	4d 63 c0             	movsxd r8,r8d
  71:	4d 63 c0             	movsxd r8,r8d
  74:	4d 63 c0             	movsxd r8,r8d
  77:	4d 63 c0             	movsxd r8,r8d
  7a:	4d 63 c0             	movsxd r8,r8d
  7d:	4d 63 c0             	movsxd r8,r8d
  80:	4d 63 c0             	movsxd r8,r8d
  83:	4d 63 c0             	movsxd r8,r8d
  86:	4d 63 c0             	movsxd r8,r8d
  89:	4d 63 c0             	movsxd r8,r8d
  8c:	4d 63 c0             	movsxd r8,r8d
  8f:	4d 63 c0             	movsxd r8,r8d
  92:	4d 63 c0             	movsxd r8,r8d
  95:	4d 63 c0             	movsxd r8,r8d
  98:	4d 63 c0             	movsxd r8,r8d
  9b:	4d 63 c0             	movsxd r8,r8d
  9e:	4d 63 c0             	movsxd r8,r8d
  a1:	4d 63 c0             	movsxd r8,r8d
  a4:	4d 63 c0             	movsxd r8,r8d
  a7:	4d 63 c0             	movsxd r8,r8d
  aa:	4d 63 c0             	movsxd r8,r8d
  ad:	4d 63 c0             	movsxd r8,r8d
  b0:	4d 63 c0             	movsxd r8,r8d
  b3:	4d 63 c0             	movsxd r8,r8d
  b6:	4d 63 c0             	movsxd r8,r8d
  b9:	4d 63 c0             	movsxd r8,r8d
  bc:	4d 63 c0             	movsxd r8,r8d
  bf:	4d 63 c0             	movsxd r8,r8d

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL

Show nanoBench command
Results:
- MPERF: 37.56
- APERF: 44.6
- UOPS: 70.0

Latency operand 3 → 1 (address, base register): 22

Experiment 1

Instruction: PDEP R8, R9, qword ptr [R14]
Chain instructions: MOVSX R8, R8D;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8
Chain latency: 63

Code:

   0:	c4 42 b3 f5 06       	pdep   r8,r9,QWORD PTR [r14]
   5:	4d 63 c0             	movsxd r8,r8d
   8:	4d 31 c6             	xor    r14,r8
   b:	4d 31 c6             	xor    r14,r8
   e:	4d 31 c6             	xor    r14,r8
  11:	4d 31 c6             	xor    r14,r8
  14:	4d 31 c6             	xor    r14,r8
  17:	4d 31 c6             	xor    r14,r8
  1a:	4d 31 c6             	xor    r14,r8
  1d:	4d 31 c6             	xor    r14,r8
  20:	4d 31 c6             	xor    r14,r8
  23:	4d 31 c6             	xor    r14,r8
  26:	4d 31 c6             	xor    r14,r8
  29:	4d 31 c6             	xor    r14,r8
  2c:	4d 31 c6             	xor    r14,r8
  2f:	4d 31 c6             	xor    r14,r8
  32:	4d 31 c6             	xor    r14,r8
  35:	4d 31 c6             	xor    r14,r8
  38:	4d 31 c6             	xor    r14,r8
  3b:	4d 31 c6             	xor    r14,r8
  3e:	4d 31 c6             	xor    r14,r8
  41:	4d 31 c6             	xor    r14,r8
  44:	4d 31 c6             	xor    r14,r8
  47:	4d 31 c6             	xor    r14,r8
  4a:	4d 31 c6             	xor    r14,r8
  4d:	4d 31 c6             	xor    r14,r8
  50:	4d 31 c6             	xor    r14,r8
  53:	4d 31 c6             	xor    r14,r8
  56:	4d 31 c6             	xor    r14,r8
  59:	4d 31 c6             	xor    r14,r8
  5c:	4d 31 c6             	xor    r14,r8
  5f:	4d 31 c6             	xor    r14,r8
  62:	4d 31 c6             	xor    r14,r8
  65:	4d 31 c6             	xor    r14,r8
  68:	4d 31 c6             	xor    r14,r8
  6b:	4d 31 c6             	xor    r14,r8
  6e:	4d 31 c6             	xor    r14,r8
  71:	4d 31 c6             	xor    r14,r8
  74:	4d 31 c6             	xor    r14,r8
  77:	4d 31 c6             	xor    r14,r8
  7a:	4d 31 c6             	xor    r14,r8
  7d:	4d 31 c6             	xor    r14,r8
  80:	4d 31 c6             	xor    r14,r8
  83:	4d 31 c6             	xor    r14,r8
  86:	4d 31 c6             	xor    r14,r8
  89:	4d 31 c6             	xor    r14,r8
  8c:	4d 31 c6             	xor    r14,r8
  8f:	4d 31 c6             	xor    r14,r8
  92:	4d 31 c6             	xor    r14,r8
  95:	4d 31 c6             	xor    r14,r8
  98:	4d 31 c6             	xor    r14,r8
  9b:	4d 31 c6             	xor    r14,r8
  9e:	4d 31 c6             	xor    r14,r8
  a1:	4d 31 c6             	xor    r14,r8
  a4:	4d 31 c6             	xor    r14,r8
  a7:	4d 31 c6             	xor    r14,r8
  aa:	4d 31 c6             	xor    r14,r8
  ad:	4d 31 c6             	xor    r14,r8
  b0:	4d 31 c6             	xor    r14,r8
  b3:	4d 31 c6             	xor    r14,r8
  b6:	4d 31 c6             	xor    r14,r8
  b9:	4d 31 c6             	xor    r14,r8
  bc:	4d 31 c6             	xor    r14,r8
  bf:	4d 31 c6             	xor    r14,r8

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL

Show nanoBench command
Results:
- MPERF: 71.64
- APERF: 85.0
- UOPS: 70.0

Latency operand 3 → 1 (address, index register): 22

Experiment 1

Instruction: PDEP R8, R9, qword ptr [R14+R13]
Chain instructions: MOVSX R8, R8D;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8
Chain latency: 63

Code:

   0:	c4 02 b3 f5 04 2e    	pdep   r8,r9,QWORD PTR [r14+r13*1]
   6:	4d 63 c0             	movsxd r8,r8d
   9:	4d 31 c5             	xor    r13,r8
   c:	4d 31 c5             	xor    r13,r8
   f:	4d 31 c5             	xor    r13,r8
  12:	4d 31 c5             	xor    r13,r8
  15:	4d 31 c5             	xor    r13,r8
  18:	4d 31 c5             	xor    r13,r8
  1b:	4d 31 c5             	xor    r13,r8
  1e:	4d 31 c5             	xor    r13,r8
  21:	4d 31 c5             	xor    r13,r8
  24:	4d 31 c5             	xor    r13,r8
  27:	4d 31 c5             	xor    r13,r8
  2a:	4d 31 c5             	xor    r13,r8
  2d:	4d 31 c5             	xor    r13,r8
  30:	4d 31 c5             	xor    r13,r8
  33:	4d 31 c5             	xor    r13,r8
  36:	4d 31 c5             	xor    r13,r8
  39:	4d 31 c5             	xor    r13,r8
  3c:	4d 31 c5             	xor    r13,r8
  3f:	4d 31 c5             	xor    r13,r8
  42:	4d 31 c5             	xor    r13,r8
  45:	4d 31 c5             	xor    r13,r8
  48:	4d 31 c5             	xor    r13,r8
  4b:	4d 31 c5             	xor    r13,r8
  4e:	4d 31 c5             	xor    r13,r8
  51:	4d 31 c5             	xor    r13,r8
  54:	4d 31 c5             	xor    r13,r8
  57:	4d 31 c5             	xor    r13,r8
  5a:	4d 31 c5             	xor    r13,r8
  5d:	4d 31 c5             	xor    r13,r8
  60:	4d 31 c5             	xor    r13,r8
  63:	4d 31 c5             	xor    r13,r8
  66:	4d 31 c5             	xor    r13,r8
  69:	4d 31 c5             	xor    r13,r8
  6c:	4d 31 c5             	xor    r13,r8
  6f:	4d 31 c5             	xor    r13,r8
  72:	4d 31 c5             	xor    r13,r8
  75:	4d 31 c5             	xor    r13,r8
  78:	4d 31 c5             	xor    r13,r8
  7b:	4d 31 c5             	xor    r13,r8
  7e:	4d 31 c5             	xor    r13,r8
  81:	4d 31 c5             	xor    r13,r8
  84:	4d 31 c5             	xor    r13,r8
  87:	4d 31 c5             	xor    r13,r8
  8a:	4d 31 c5             	xor    r13,r8
  8d:	4d 31 c5             	xor    r13,r8
  90:	4d 31 c5             	xor    r13,r8
  93:	4d 31 c5             	xor    r13,r8
  96:	4d 31 c5             	xor    r13,r8
  99:	4d 31 c5             	xor    r13,r8
  9c:	4d 31 c5             	xor    r13,r8
  9f:	4d 31 c5             	xor    r13,r8
  a2:	4d 31 c5             	xor    r13,r8
  a5:	4d 31 c5             	xor    r13,r8
  a8:	4d 31 c5             	xor    r13,r8
  ab:	4d 31 c5             	xor    r13,r8
  ae:	4d 31 c5             	xor    r13,r8
  b1:	4d 31 c5             	xor    r13,r8
  b4:	4d 31 c5             	xor    r13,r8
  b7:	4d 31 c5             	xor    r13,r8
  ba:	4d 31 c5             	xor    r13,r8
  bd:	4d 31 c5             	xor    r13,r8
  c0:	4d 31 c5             	xor    r13,r8

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 71.64
- APERF: 85.0
- UOPS: 70.0

Latency operand 3 → 1 (memory): ≤25

Experiment 1

Instruction: PDEP R8, R9, qword ptr [R14]
Chain instructions: MOVSX R12, R8D;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12
Chain latency: ≥62

Code:

   0:	c4 42 b3 f5 06       	pdep   r8,r9,QWORD PTR [r14]
   5:	4d 63 e0             	movsxd r12,r8d
   8:	4d 63 e4             	movsxd r12,r12d
   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 89 26             	mov    QWORD PTR [r14],r12

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL

Show nanoBench command
Results:
- MPERF: 73.26
- APERF: 87.0
- UOPS: 70.0

PDEP (R64, R64, M64) - Latency

Operands

Latency operand 2 → 1: 0

Latency operand 3 → 1 (address, base register): 22

Latency operand 3 → 1 (address, index register): 22

Latency operand 3 → 1 (memory): ≤25

Latency operand 2 → 1: 0

Experiment 1

Latency operand 3 → 1 (address, base register): 22

Experiment 1

Latency operand 3 → 1 (address, index register): 22

Experiment 1

Latency operand 3 → 1 (memory): ≤25

Experiment 1