DIVSS (XMM, XMM)

Experiment 1

Instruction: DIVSS XMM3, XMM4
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;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: ≥22

Code:

   0:	f3 0f 5e dc          	divss  xmm3,xmm4
   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
  2e:	0f 56 db             	orps   xmm3,xmm3
  31:	0f 56 db             	orps   xmm3,xmm3
  34:	0f 56 db             	orps   xmm3,xmm3
  37:	0f 56 db             	orps   xmm3,xmm3
  3a:	0f 56 db             	orps   xmm3,xmm3
  3d:	0f 56 db             	orps   xmm3,xmm3
  40:	0f 56 db             	orps   xmm3,xmm3
  43:	0f 56 db             	orps   xmm3,xmm3

Init:

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: 23.0
- Core cycles: 41.01
- Reference cycles: 25.61
- UOPS_RETIRED.ANY: 23.0

Experiment 2

Instruction: DIVSS XMM3, XMM3

Code:

   0:	f3 0f 5e db          	divss  xmm3,xmm3

Init:

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: 18.99
- Reference cycles: 12.48
- UOPS_RETIRED.ANY: 1.0

Experiment 3

Instruction: DIVSS XMM3, XMM4
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;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: ≥20

Code:

   0:	f3 0f 5e dc          	divss  xmm3,xmm4
   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
  28:	0f 56 db             	orps   xmm3,xmm3
  2b:	0f 56 db             	orps   xmm3,xmm3
  2e:	0f 56 db             	orps   xmm3,xmm3
  31:	0f 56 db             	orps   xmm3,xmm3
  34:	0f 56 db             	orps   xmm3,xmm3
  37:	0f 56 db             	orps   xmm3,xmm3
  3a:	0f 56 db             	orps   xmm3,xmm3
  3d:	0f 56 db             	orps   xmm3,xmm3

Init:

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: 21.0
- Core cycles: 39.0
- Reference cycles: 25.22
- UOPS_RETIRED.ANY: 21.0

Experiment 1

Instruction: DIVSS XMM3, XMM4
Chain instructions: ANDPS XMM4, XMM3; MOVUPS XMM3, XMM1; ANDPS XMM4, XMM2; ORPS XMM4, XMM2; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4;
Chain latency: ≥23

Code:

   0:	f3 0f 5e dc          	divss  xmm3,xmm4
   4:	0f 54 e3             	andps  xmm4,xmm3
   7:	0f 10 d9             	movups xmm3,xmm1
   a:	0f 54 e2             	andps  xmm4,xmm2
   d:	0f 56 e2             	orps   xmm4,xmm2
  10:	0f 56 e4             	orps   xmm4,xmm4
  13:	0f 56 e4             	orps   xmm4,xmm4
  16:	0f 56 e4             	orps   xmm4,xmm4
  19:	0f 56 e4             	orps   xmm4,xmm4
  1c:	0f 56 e4             	orps   xmm4,xmm4
  1f:	0f 56 e4             	orps   xmm4,xmm4
  22:	0f 56 e4             	orps   xmm4,xmm4
  25:	0f 56 e4             	orps   xmm4,xmm4
  28:	0f 56 e4             	orps   xmm4,xmm4
  2b:	0f 56 e4             	orps   xmm4,xmm4
  2e:	0f 56 e4             	orps   xmm4,xmm4
  31:	0f 56 e4             	orps   xmm4,xmm4
  34:	0f 56 e4             	orps   xmm4,xmm4
  37:	0f 56 e4             	orps   xmm4,xmm4
  3a:	0f 56 e4             	orps   xmm4,xmm4
  3d:	0f 56 e4             	orps   xmm4,xmm4
  40:	0f 56 e4             	orps   xmm4,xmm4
  43:	0f 56 e4             	orps   xmm4,xmm4
  46:	0f 56 e4             	orps   xmm4,xmm4
  49:	0f 56 e4             	orps   xmm4,xmm4

Init:

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: 25.0
- Core cycles: 41.99
- Reference cycles: 27.69
- UOPS_RETIRED.ANY: 25.0

Experiment 2

Instruction: DIVSS XMM3, XMM3

Code:

   0:	f3 0f 5e db          	divss  xmm3,xmm3

Init:

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: 18.99
- Reference cycles: 12.48
- UOPS_RETIRED.ANY: 1.0

Experiment 3

Instruction: DIVSS XMM3, XMM4
Chain instructions: ANDPS XMM4, XMM3; ANDPS XMM4, XMM2; ORPS XMM4, XMM2; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4; ORPS XMM4, XMM4;
Chain latency: ≥23

Code:

   0:	f3 0f 5e dc          	divss  xmm3,xmm4
   4:	0f 54 e3             	andps  xmm4,xmm3
   7:	0f 54 e2             	andps  xmm4,xmm2
   a:	0f 56 e2             	orps   xmm4,xmm2
   d:	0f 56 e4             	orps   xmm4,xmm4
  10:	0f 56 e4             	orps   xmm4,xmm4
  13:	0f 56 e4             	orps   xmm4,xmm4
  16:	0f 56 e4             	orps   xmm4,xmm4
  19:	0f 56 e4             	orps   xmm4,xmm4
  1c:	0f 56 e4             	orps   xmm4,xmm4
  1f:	0f 56 e4             	orps   xmm4,xmm4
  22:	0f 56 e4             	orps   xmm4,xmm4
  25:	0f 56 e4             	orps   xmm4,xmm4
  28:	0f 56 e4             	orps   xmm4,xmm4
  2b:	0f 56 e4             	orps   xmm4,xmm4
  2e:	0f 56 e4             	orps   xmm4,xmm4
  31:	0f 56 e4             	orps   xmm4,xmm4
  34:	0f 56 e4             	orps   xmm4,xmm4
  37:	0f 56 e4             	orps   xmm4,xmm4
  3a:	0f 56 e4             	orps   xmm4,xmm4
  3d:	0f 56 e4             	orps   xmm4,xmm4
  40:	0f 56 e4             	orps   xmm4,xmm4
  43:	0f 56 e4             	orps   xmm4,xmm4
  46:	0f 56 e4             	orps   xmm4,xmm4

Init:

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: 24.0
- Core cycles: 42.0
- Reference cycles: 27.95
- UOPS_RETIRED.ANY: 24.0

DIVSS (XMM, XMM) - Latency

Operands

Latency operand 1 → 1: ≤19

Latency operand 2 → 1: ≤19

Latency operand 1 → 1: ≤19

Experiment 1

Experiment 2

Experiment 3

Latency operand 2 → 1: ≤19

Experiment 1

Experiment 2

Experiment 3