BTS (M64, 0) - Latency

Experiment 1

• Instruction: BTS qword ptr [R14], 0
• Chain instructions: MOV R12, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12
• Chain latency: ≥6
• Code:

     0:	49 0f ba 2e 00       	bts    QWORD PTR [r14],0x0
     5:	4d 8b 26             	mov    r12,QWORD PTR [r14]
     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 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
  

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 10.93
  • Reference cycles: 9.43
  • UOPS_RETIRED.ALL: 8.0

Experiment 2 (with additional nop)

• Instruction: BTS qword ptr [R14], 0
• Chain instructions: MOV R12, [R14];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R14, R12; XOR R14, R12;nop
• Chain latency: ≥6
• Code:

     0:	49 0f ba 2e 00       	bts    QWORD PTR [r14],0x0
     5:	4d 8b 26             	mov    r12,QWORD PTR [r14]
     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 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	90                   	nop
  

• Show nanoBench command
• Results:
  • Instructions retired: 9.0
  • Core cycles: 11.11
  • Reference cycles: 9.09
  • UOPS_RETIRED.ALL: 9.0

Experiment 1

• Instruction: BTS qword ptr [R14+R13], 0
• Chain instructions: MOV R12, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12
• Chain latency: ≥6
• Code:

     0:	4b 0f ba 2c 2e 00    	bts    QWORD PTR [r14+r13*1],0x0
     6:	4f 8b 24 2e          	mov    r12,QWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 31 e5             	xor    r13,r12
    19:	4d 31 e5             	xor    r13,r12
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 11.07
  • Reference cycles: 9.43
  • UOPS_RETIRED.ALL: 8.0

Experiment 2 (with additional nop)

• Instruction: BTS qword ptr [R14+R13], 0
• Chain instructions: MOV R12, [R14+R13];MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;MOVSX R12, R12D;XOR R13, R12; XOR R13, R12;nop
• Chain latency: ≥6
• Code:

     0:	4b 0f ba 2c 2e 00    	bts    QWORD PTR [r14+r13*1],0x0
     6:	4f 8b 24 2e          	mov    r12,QWORD PTR [r14+r13*1]
     a:	4d 63 e4             	movsxd r12,r12d
     d:	4d 63 e4             	movsxd r12,r12d
    10:	4d 63 e4             	movsxd r12,r12d
    13:	4d 63 e4             	movsxd r12,r12d
    16:	4d 31 e5             	xor    r13,r12
    19:	4d 31 e5             	xor    r13,r12
    1c:	90                   	nop
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 9.0
  • Core cycles: 11.09
  • Reference cycles: 9.09
  • UOPS_RETIRED.ALL: 9.0

Experiment 1

• Instruction: BTS qword ptr [R14], 0
• Code:

     0:	49 0f ba 2e 00       	bts    QWORD PTR [r14],0x0
  

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 1.24
  • Reference cycles: 1.52
  • UOPS_RETIRED.ALL: 1.0

Experiment 2

• Instruction: BTS qword ptr [R14], 0
• 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;MOV [R14], R12
• Chain latency: 10
• Code:

     0:	49 0f ba 2e 00       	bts    QWORD PTR [r14],0x0
     5:	4d 8b 26             	mov    r12,QWORD PTR [r14]
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 12.56
  • Reference cycles: 10.61
  • UOPS_RETIRED.ALL: 13.0

Experiment 1

• Instruction: BTS qword ptr [R14], 0
• Chain instruction: CMOVC R14, R14
• Chain latency: 2
• Code:

     0:	49 0f ba 2e 00       	bts    QWORD PTR [r14],0x0
     5:	4d 0f 42 f6          	cmovb  r14,r14
  

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 1.99
  • Reference cycles: 1.68
  • UOPS_RETIRED.ALL: 2.0

Experiment 1

• Instruction: BTS qword ptr [R14+R13], 0
• Chain instruction: CMOVC R13, R13
• Chain latency: 2
• Code:

     0:	4b 0f ba 2c 2e 00    	bts    QWORD PTR [r14+r13*1],0x0
     6:	4d 0f 42 ed          	cmovb  r13,r13
  

• Init:

  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 2.0
  • Reference cycles: 1.85
  • UOPS_RETIRED.ALL: 2.0

Experiment 1

• Instruction: BTS qword ptr [R14], 0
• Chain instructions: CMOVC R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12
• Chain latency: ≥6
• Code:

     0:	49 0f ba 2e 00       	bts    QWORD PTR [r14],0x0
     5:	4d 0f 42 e4          	cmovb  r12,r12
     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 89 26             	mov    QWORD PTR [r14],r12
  

• Show nanoBench command
• Results:
  • Instructions retired: 7.0
  • Core cycles: 7.97
  • Reference cycles: 7.07
  • UOPS_RETIRED.ALL: 7.0