MOVSQ - Latency

Experiment 1

• Instruction: MOVSQ
• Chain instructions: MOV R12, [RDI];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR RDI, R12; XOR RDI, R12;TEST R15, R15
• Chain latency: ≥9
• Code:

     0:	48 a5                	movs   QWORD PTR es:[rdi],QWORD PTR ds:[rsi]
     2:	4c 8b 27             	mov    r12,QWORD PTR [rdi]
     5:	4d 63 e4             	movsxd r12,r12d
     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:	4c 31 e7             	xor    rdi,r12
    1a:	4c 31 e7             	xor    rdi,r12
    1d:	4d 85 ff             	test   r15,r15
  

• Show nanoBench command
• Results:
  • Instructions retired: 11.0
  • Core cycles: 16.95
  • Reference cycles: 14.2
  • UOPS_RETIRED.ANY: 15.0

Experiment 2 (with additional nop)

• Instruction: MOVSQ
• Chain instructions: MOV R12, [RDI];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR RDI, R12; XOR RDI, R12;TEST R15, R15;nop
• Chain latency: ≥9
• Code:

     0:	48 a5                	movs   QWORD PTR es:[rdi],QWORD PTR ds:[rsi]
     2:	4c 8b 27             	mov    r12,QWORD PTR [rdi]
     5:	4d 63 e4             	movsxd r12,r12d
     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:	4c 31 e7             	xor    rdi,r12
    1a:	4c 31 e7             	xor    rdi,r12
    1d:	4d 85 ff             	test   r15,r15
    20:	90                   	nop
  

• Show nanoBench command
• Results:
  • Instructions retired: 12.0
  • Core cycles: 16.96
  • Reference cycles: 14.17
  • UOPS_RETIRED.ANY: 16.0