DIVPS (XMM, M128) - Latency

Experiment 1

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: ORPS XMM3, XMM1; ANDPS XMM3, XMM1; ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3
• Chain latency: ≥14
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	0f 56 d9             	orps   xmm3,xmm1
     7:	0f 54 d9             	andps  xmm3,xmm1
     a:	0f 56 db             	orps   xmm3,xmm3
     d:	0f 56 db             	orps   xmm3,xmm3
    10:	0f 56 db             	orps   xmm3,xmm3
    13:	0f 56 db             	orps   xmm3,xmm3
    16:	0f 56 db             	orps   xmm3,xmm3
    19:	0f 56 db             	orps   xmm3,xmm3
    1c:	0f 56 db             	orps   xmm3,xmm3
    1f:	0f 56 db             	orps   xmm3,xmm3
    22:	0f 56 db             	orps   xmm3,xmm3
    25:	0f 56 db             	orps   xmm3,xmm3
    28:	0f 56 db             	orps   xmm3,xmm3
    2b:	0f 56 db             	orps   xmm3,xmm3
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 31.0
  • Reference cycles: 31.36
  • UOPS_RETIRED.ALL: 15.0

Experiment 2

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 15.0
  • Reference cycles: 15.2
  • UOPS_RETIRED.ALL: 1.0

Experiment 3

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3;ORPS XMM3, XMM3
• Chain latency: ≥12
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	0f 56 db             	orps   xmm3,xmm3
     7:	0f 56 db             	orps   xmm3,xmm3
     a:	0f 56 db             	orps   xmm3,xmm3
     d:	0f 56 db             	orps   xmm3,xmm3
    10:	0f 56 db             	orps   xmm3,xmm3
    13:	0f 56 db             	orps   xmm3,xmm3
    16:	0f 56 db             	orps   xmm3,xmm3
    19:	0f 56 db             	orps   xmm3,xmm3
    1c:	0f 56 db             	orps   xmm3,xmm3
    1f:	0f 56 db             	orps   xmm3,xmm3
    22:	0f 56 db             	orps   xmm3,xmm3
    25:	0f 56 db             	orps   xmm3,xmm3
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 13.0
  • Core cycles: 29.0
  • Reference cycles: 29.92
  • UOPS_RETIRED.ALL: 13.0

Experiment 1

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: EXTRACTPS R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 17 dc 02 	extractps r12d,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.76
  • UOPS_RETIRED.ALL: 15.0

Experiment 2

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVD R12D, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 7e dc       	movd   r12d,xmm3
     9:	0f 10 d9             	movups xmm3,xmm1
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
    2d:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 3

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVMSKPS R12D, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	44 0f 50 e3          	movmskps r12d,xmm3
     8:	0f 10 d9             	movups xmm3,xmm1
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 38.08
  • UOPS_RETIRED.ALL: 15.0

Experiment 4

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVQ R12, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 7e dc       	movq   r12,xmm3
     9:	0f 10 d9             	movups xmm3,xmm1
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
    2d:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.6
  • UOPS_RETIRED.ALL: 15.0

Experiment 5

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRB R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 14 dc 02 	pextrb r12d,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 6

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRD R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 16 dc 02 	pextrd r12d,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 38.4
  • UOPS_RETIRED.ALL: 15.0

Experiment 7

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRQ R12, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 3a 16 dc 02 	pextrq r12,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 8

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRW R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f c5 e3 02    	pextrw r12d,xmm3,0x2
     a:	0f 10 d9             	movups xmm3,xmm1
     d:	4d 31 e6             	xor    r14,r12
    10:	4d 31 e6             	xor    r14,r12
    13:	4d 31 e6             	xor    r14,r12
    16:	4d 31 e6             	xor    r14,r12
    19:	4d 31 e6             	xor    r14,r12
    1c:	4d 31 e6             	xor    r14,r12
    1f:	4d 31 e6             	xor    r14,r12
    22:	4d 31 e6             	xor    r14,r12
    25:	4d 31 e6             	xor    r14,r12
    28:	4d 31 e6             	xor    r14,r12
    2b:	4d 31 e6             	xor    r14,r12
    2e:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 38.24
  • UOPS_RETIRED.ALL: 15.0

Experiment 9

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PMOVMSKB R12D, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f d7 e3       	pmovmskb r12d,xmm3
     9:	0f 10 d9             	movups xmm3,xmm1
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
    2d:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.76
  • UOPS_RETIRED.ALL: 15.0

Experiment 10

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: EXTRACTPS R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 17 dc 02 	extractps r12d,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.76
  • UOPS_RETIRED.ALL: 14.0

Experiment 11

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVD R12D, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 7e dc       	movd   r12d,xmm3
     9:	4d 31 e6             	xor    r14,r12
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.76
  • UOPS_RETIRED.ALL: 14.0

Experiment 12

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVMSKPS R12D, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	44 0f 50 e3          	movmskps r12d,xmm3
     8:	4d 31 e6             	xor    r14,r12
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0

Experiment 13

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVQ R12, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 7e dc       	movq   r12,xmm3
     9:	4d 31 e6             	xor    r14,r12
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0

Experiment 14

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRB R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 14 dc 02 	pextrb r12d,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0

Experiment 15

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRD R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 16 dc 02 	pextrd r12d,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0

Experiment 16

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRQ R12, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 3a 16 dc 02 	pextrq r12,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0

Experiment 17

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRW R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f c5 e3 02    	pextrw r12d,xmm3,0x2
     a:	4d 31 e6             	xor    r14,r12
     d:	4d 31 e6             	xor    r14,r12
    10:	4d 31 e6             	xor    r14,r12
    13:	4d 31 e6             	xor    r14,r12
    16:	4d 31 e6             	xor    r14,r12
    19:	4d 31 e6             	xor    r14,r12
    1c:	4d 31 e6             	xor    r14,r12
    1f:	4d 31 e6             	xor    r14,r12
    22:	4d 31 e6             	xor    r14,r12
    25:	4d 31 e6             	xor    r14,r12
    28:	4d 31 e6             	xor    r14,r12
    2b:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 38.08
  • UOPS_RETIRED.ALL: 14.0

Experiment 18

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PMOVMSKB R12D, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f d7 e3       	pmovmskb r12d,xmm3
     9:	4d 31 e6             	xor    r14,r12
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.76
  • UOPS_RETIRED.ALL: 14.0

Experiment 1

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: EXTRACTPS R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 17 dc 02 	extractps r12d,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 2

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVD R12D, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 7e dc       	movd   r12d,xmm3
     9:	0f 10 d9             	movups xmm3,xmm1
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
    2d:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.44
  • UOPS_RETIRED.ALL: 15.0

Experiment 3

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVMSKPS R12D, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	44 0f 50 e3          	movmskps r12d,xmm3
     8:	0f 10 d9             	movups xmm3,xmm1
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 4

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVQ R12, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 7e dc       	movq   r12,xmm3
     9:	0f 10 d9             	movups xmm3,xmm1
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
    2d:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 5

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRB R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 14 dc 02 	pextrb r12d,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 6

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRD R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 16 dc 02 	pextrd r12d,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 7

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRQ R12, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 3a 16 dc 02 	pextrq r12,xmm3,0x2
     b:	0f 10 d9             	movups xmm3,xmm1
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
    2f:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 8

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRW R12D, XMM3, 2; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f c5 e3 02    	pextrw r12d,xmm3,0x2
     a:	0f 10 d9             	movups xmm3,xmm1
     d:	4d 31 e6             	xor    r14,r12
    10:	4d 31 e6             	xor    r14,r12
    13:	4d 31 e6             	xor    r14,r12
    16:	4d 31 e6             	xor    r14,r12
    19:	4d 31 e6             	xor    r14,r12
    1c:	4d 31 e6             	xor    r14,r12
    1f:	4d 31 e6             	xor    r14,r12
    22:	4d 31 e6             	xor    r14,r12
    25:	4d 31 e6             	xor    r14,r12
    28:	4d 31 e6             	xor    r14,r12
    2b:	4d 31 e6             	xor    r14,r12
    2e:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 38.08
  • UOPS_RETIRED.ALL: 15.0

Experiment 9

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PMOVMSKB R12D, XMM3; MOVUPS XMM3, XMM1; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f d7 e3       	pmovmskb r12d,xmm3
     9:	0f 10 d9             	movups xmm3,xmm1
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
    2d:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x54ed392654ed3926;
  MOV RBX, 0x3f99f4c03f99f4c0;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 15.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 15.0

Experiment 10

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: EXTRACTPS R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 17 dc 02 	extractps r12d,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 38.08
  • UOPS_RETIRED.ALL: 14.0

Experiment 11

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVD R12D, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 7e dc       	movd   r12d,xmm3
     9:	4d 31 e6             	xor    r14,r12
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 38.08
  • UOPS_RETIRED.ALL: 14.0

Experiment 12

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVMSKPS R12D, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	44 0f 50 e3          	movmskps r12d,xmm3
     8:	4d 31 e6             	xor    r14,r12
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0

Experiment 13

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: MOVQ R12, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 7e dc       	movq   r12,xmm3
     9:	4d 31 e6             	xor    r14,r12
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0

Experiment 14

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRB R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 14 dc 02 	pextrb r12d,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 38.08
  • UOPS_RETIRED.ALL: 14.0

Experiment 15

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRD R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 41 0f 3a 16 dc 02 	pextrd r12d,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.76
  • UOPS_RETIRED.ALL: 14.0

Experiment 16

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRQ R12, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 49 0f 3a 16 dc 02 	pextrq r12,xmm3,0x2
     b:	4d 31 e6             	xor    r14,r12
     e:	4d 31 e6             	xor    r14,r12
    11:	4d 31 e6             	xor    r14,r12
    14:	4d 31 e6             	xor    r14,r12
    17:	4d 31 e6             	xor    r14,r12
    1a:	4d 31 e6             	xor    r14,r12
    1d:	4d 31 e6             	xor    r14,r12
    20:	4d 31 e6             	xor    r14,r12
    23:	4d 31 e6             	xor    r14,r12
    26:	4d 31 e6             	xor    r14,r12
    29:	4d 31 e6             	xor    r14,r12
    2c:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.76
  • UOPS_RETIRED.ALL: 14.0

Experiment 17

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PEXTRW R12D, XMM3, 2; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f c5 e3 02    	pextrw r12d,xmm3,0x2
     a:	4d 31 e6             	xor    r14,r12
     d:	4d 31 e6             	xor    r14,r12
    10:	4d 31 e6             	xor    r14,r12
    13:	4d 31 e6             	xor    r14,r12
    16:	4d 31 e6             	xor    r14,r12
    19:	4d 31 e6             	xor    r14,r12
    1c:	4d 31 e6             	xor    r14,r12
    1f:	4d 31 e6             	xor    r14,r12
    22:	4d 31 e6             	xor    r14,r12
    25:	4d 31 e6             	xor    r14,r12
    28:	4d 31 e6             	xor    r14,r12
    2b:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 38.08
  • UOPS_RETIRED.ALL: 14.0

Experiment 18

• Instruction: DIVPS XMM3, xmmword ptr [R14]
• Chain instructions: PMOVMSKB R12D, XMM3; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12; XOR R14, R12;
• Chain latency: ≥13
• Code:

     0:	41 0f 5e 1e          	divps  xmm3,XMMWORD PTR [r14]
     4:	66 44 0f d7 e3       	pmovmskb r12d,xmm3
     9:	4d 31 e6             	xor    r14,r12
     c:	4d 31 e6             	xor    r14,r12
     f:	4d 31 e6             	xor    r14,r12
    12:	4d 31 e6             	xor    r14,r12
    15:	4d 31 e6             	xor    r14,r12
    18:	4d 31 e6             	xor    r14,r12
    1b:	4d 31 e6             	xor    r14,r12
    1e:	4d 31 e6             	xor    r14,r12
    21:	4d 31 e6             	xor    r14,r12
    24:	4d 31 e6             	xor    r14,r12
    27:	4d 31 e6             	xor    r14,r12
    2a:	4d 31 e6             	xor    r14,r12
  

• Init:

  VZEROALL;
  MOV RAX, 0x3f8000003f800000;
  MOV RBX, 0x3f8000003f800000;
  MOV [R14+0], RBX;
  MOV [R14+8], RBX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOVUPS XMM1, [R14+64];
  MOVUPS XMM2, [R14];
  MOVUPS XMM3, [R14+64];
  MOVUPS XMM4, [R14]

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 37.0
  • Reference cycles: 37.92
  • UOPS_RETIRED.ALL: 14.0