CRC32 (R64, R64) - Latency

Experiment 1 (with R9=0)

• Instruction: CRC32 R8, R9
• Code:

     0:	f2 4d 0f 38 f1 c1    	crc32  r8,r9
  

• Init:

  MOV R9, 0

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 3.0
  • Reference cycles: 2.5
  • UOPS_RETIRED.ANY: 1.0

Experiment 2 (with R9=1)

• Instruction: CRC32 R8, R9
• Code:

     0:	f2 4d 0f 38 f1 c1    	crc32  r8,r9
  

• Init:

  MOV R9, 1

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 3.0
  • Reference cycles: 2.5
  • UOPS_RETIRED.ANY: 1.0

Experiment 3 (with R9=2)

• Instruction: CRC32 R8, R9
• Code:

     0:	f2 4d 0f 38 f1 c1    	crc32  r8,r9
  

• Init:

  MOV R9, 2

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 3.0
  • Reference cycles: 2.5
  • UOPS_RETIRED.ANY: 1.0

Experiment 4 (with R9=0)

• Instruction: CRC32 R8, R9
• Chain instructions: MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 7
• Code:

     0:	f2 4d 0f 38 f1 c1    	crc32  r8,r9
     6:	4d 63 c0             	movsxd r8,r8d
     9:	4d 63 c0             	movsxd r8,r8d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
  

• Init:

  MOV R9, 0

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 10.0
  • Reference cycles: 8.3
  • UOPS_RETIRED.ANY: 8.0

Experiment 5 (with R9=1)

• Instruction: CRC32 R8, R9
• Chain instructions: MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 7
• Code:

     0:	f2 4d 0f 38 f1 c1    	crc32  r8,r9
     6:	4d 63 c0             	movsxd r8,r8d
     9:	4d 63 c0             	movsxd r8,r8d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
  

• Init:

  MOV R9, 1

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 10.0
  • Reference cycles: 8.27
  • UOPS_RETIRED.ANY: 8.0

Experiment 6 (with R9=2)

• Instruction: CRC32 R8, R9
• Chain instructions: MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 7
• Code:

     0:	f2 4d 0f 38 f1 c1    	crc32  r8,r9
     6:	4d 63 c0             	movsxd r8,r8d
     9:	4d 63 c0             	movsxd r8,r8d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
  

• Init:

  MOV R9, 2

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 10.0
  • Reference cycles: 8.2
  • UOPS_RETIRED.ANY: 8.0

Experiment 1

• Instruction: CRC32 R9, R8
• Chain instructions: MOVSX R8, R9D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
• Chain latency: 7
• Code:

     0:	f2 4d 0f 38 f1 c8    	crc32  r9,r8
     6:	4d 63 c1             	movsxd r8,r9d
     9:	4d 63 c0             	movsxd r8,r8d
     c:	4d 63 c0             	movsxd r8,r8d
     f:	4d 63 c0             	movsxd r8,r8d
    12:	4d 63 c0             	movsxd r8,r8d
    15:	4d 63 c0             	movsxd r8,r8d
    18:	4d 63 c0             	movsxd r8,r8d
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 10.0
  • Reference cycles: 8.23
  • UOPS_RETIRED.ANY: 8.0