ROL (R32, I8) - Throughput and Uops

With unroll_count=500 and no inner loop

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 0.68
  • APERF: 1.0
  • UOPS: 1.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 0.69
  • APERF: 1.0
  • UOPS: 1.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 0.68
  • APERF: 1.0
  • UOPS: 1.01
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With additional dependency-breaking instructions

With unroll_count=500 and no inner loop

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 0.68
  • APERF: 1.0
  • UOPS: 2.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 0.68
  • APERF: 1.0
  • UOPS: 2.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 0.68
  • APERF: 1.0
  • UOPS: 2.01
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With unroll_count=200 and no inner loop

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.05
  • APERF: 1.5
  • UOPS: 4.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.33
  • APERF: 1.94
  • UOPS: 4.5
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.04
  • APERF: 1.52
  • UOPS: 4.05
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With additional dependency-breaking instructions

With unroll_count=200 and no inner loop

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.14
  • APERF: 1.63
  • UOPS: 5.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.16
  • APERF: 1.7
  • UOPS: 5.5
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.06
  • APERF: 1.55
  • UOPS: 5.05
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=200 and no inner loop

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.43
  • APERF: 2.0
  • UOPS: 8.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.35
  • APERF: 1.98
  • UOPS: 8.5
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.03
  • APERF: 1.49
  • UOPS: 8.05
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With unroll_count=100 and no inner loop

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
    10:	41 c1 c4 02          	rol    r12d,0x2
    14:	41 c1 c5 02          	rol    r13d,0x2
    18:	41 c1 c6 02          	rol    r14d,0x2
    1c:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.84
  • APERF: 2.67
  • UOPS: 8.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
    10:	41 c1 c4 02          	rol    r12d,0x2
    14:	41 c1 c5 02          	rol    r13d,0x2
    18:	41 c1 c6 02          	rol    r14d,0x2
    1c:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 2.32
  • APERF: 3.39
  • UOPS: 9.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
    10:	41 c1 c4 02          	rol    r12d,0x2
    14:	41 c1 c5 02          	rol    r13d,0x2
    18:	41 c1 c6 02          	rol    r14d,0x2
    1c:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.86
  • APERF: 2.7
  • UOPS: 8.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With additional dependency-breaking instructions

With unroll_count=100 and no inner loop

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
    13:	41 c1 c4 02          	rol    r12d,0x2
    17:	41 c1 c5 02          	rol    r13d,0x2
    1b:	41 c1 c6 02          	rol    r14d,0x2
    1f:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.9
  • APERF: 2.81
  • UOPS: 9.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
    13:	41 c1 c4 02          	rol    r12d,0x2
    17:	41 c1 c5 02          	rol    r13d,0x2
    1b:	41 c1 c6 02          	rol    r14d,0x2
    1f:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 2.08
  • APERF: 3.03
  • UOPS: 10.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
    13:	41 c1 c4 02          	rol    r12d,0x2
    17:	41 c1 c5 02          	rol    r13d,0x2
    1b:	41 c1 c6 02          	rol    r14d,0x2
    1f:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 1.94
  • APERF: 2.83
  • UOPS: 9.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=100 and no inner loop

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
    1c:	4d 85 ff             	test   r15,r15
    1f:	41 c1 c4 02          	rol    r12d,0x2
    23:	4d 85 ff             	test   r15,r15
    26:	41 c1 c5 02          	rol    r13d,0x2
    2a:	4d 85 ff             	test   r15,r15
    2d:	41 c1 c6 02          	rol    r14d,0x2
    31:	4d 85 ff             	test   r15,r15
    34:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 2.66
  • APERF: 4.0
  • UOPS: 16.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
    1c:	4d 85 ff             	test   r15,r15
    1f:	41 c1 c4 02          	rol    r12d,0x2
    23:	4d 85 ff             	test   r15,r15
    26:	41 c1 c5 02          	rol    r13d,0x2
    2a:	4d 85 ff             	test   r15,r15
    2d:	41 c1 c6 02          	rol    r14d,0x2
    31:	4d 85 ff             	test   r15,r15
    34:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 2.39
  • APERF: 3.48
  • UOPS: 17.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
    1c:	4d 85 ff             	test   r15,r15
    1f:	41 c1 c4 02          	rol    r12d,0x2
    23:	4d 85 ff             	test   r15,r15
    26:	41 c1 c5 02          	rol    r13d,0x2
    2a:	4d 85 ff             	test   r15,r15
    2d:	41 c1 c6 02          	rol    r14d,0x2
    31:	4d 85 ff             	test   r15,r15
    34:	c1 c3 02             	rol    ebx,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 2.03
  • APERF: 2.97
  • UOPS: 16.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With unroll_count=100 and no inner loop

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
    10:	41 c1 c4 02          	rol    r12d,0x2
    14:	41 c1 c5 02          	rol    r13d,0x2
    18:	41 c1 c6 02          	rol    r14d,0x2
    1c:	c1 c3 02             	rol    ebx,0x2
    1f:	c1 c1 02             	rol    ecx,0x2
    22:	c1 c2 02             	rol    edx,0x2
    25:	c1 c0 02             	rol    eax,0x2
    28:	c1 c7 02             	rol    edi,0x2
    2b:	c1 c6 02             	rol    esi,0x2
    2e:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.29
  • APERF: 4.66
  • UOPS: 14.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
    10:	41 c1 c4 02          	rol    r12d,0x2
    14:	41 c1 c5 02          	rol    r13d,0x2
    18:	41 c1 c6 02          	rol    r14d,0x2
    1c:	c1 c3 02             	rol    ebx,0x2
    1f:	c1 c1 02             	rol    ecx,0x2
    22:	c1 c2 02             	rol    edx,0x2
    25:	c1 c0 02             	rol    eax,0x2
    28:	c1 c7 02             	rol    edi,0x2
    2b:	c1 c6 02             	rol    esi,0x2
    2e:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.45
  • APERF: 5.02
  • UOPS: 15.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	41 c1 c0 02          	rol    r8d,0x2
     4:	41 c1 c1 02          	rol    r9d,0x2
     8:	41 c1 c2 02          	rol    r10d,0x2
     c:	41 c1 c3 02          	rol    r11d,0x2
    10:	41 c1 c4 02          	rol    r12d,0x2
    14:	41 c1 c5 02          	rol    r13d,0x2
    18:	41 c1 c6 02          	rol    r14d,0x2
    1c:	c1 c3 02             	rol    ebx,0x2
    1f:	c1 c1 02             	rol    ecx,0x2
    22:	c1 c2 02             	rol    edx,0x2
    25:	c1 c0 02             	rol    eax,0x2
    28:	c1 c7 02             	rol    edi,0x2
    2b:	c1 c6 02             	rol    esi,0x2
    2e:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.22
  • APERF: 4.7
  • UOPS: 14.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With additional dependency-breaking instructions

With unroll_count=100 and no inner loop

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
    13:	41 c1 c4 02          	rol    r12d,0x2
    17:	41 c1 c5 02          	rol    r13d,0x2
    1b:	41 c1 c6 02          	rol    r14d,0x2
    1f:	c1 c3 02             	rol    ebx,0x2
    22:	c1 c1 02             	rol    ecx,0x2
    25:	c1 c2 02             	rol    edx,0x2
    28:	c1 c0 02             	rol    eax,0x2
    2b:	c1 c7 02             	rol    edi,0x2
    2e:	c1 c6 02             	rol    esi,0x2
    31:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.23
  • APERF: 4.67
  • UOPS: 15.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
    13:	41 c1 c4 02          	rol    r12d,0x2
    17:	41 c1 c5 02          	rol    r13d,0x2
    1b:	41 c1 c6 02          	rol    r14d,0x2
    1f:	c1 c3 02             	rol    ebx,0x2
    22:	c1 c1 02             	rol    ecx,0x2
    25:	c1 c2 02             	rol    edx,0x2
    28:	c1 c0 02             	rol    eax,0x2
    2b:	c1 c7 02             	rol    edi,0x2
    2e:	c1 c6 02             	rol    esi,0x2
    31:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.47
  • APERF: 5.08
  • UOPS: 16.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	41 c1 c1 02          	rol    r9d,0x2
     b:	41 c1 c2 02          	rol    r10d,0x2
     f:	41 c1 c3 02          	rol    r11d,0x2
    13:	41 c1 c4 02          	rol    r12d,0x2
    17:	41 c1 c5 02          	rol    r13d,0x2
    1b:	41 c1 c6 02          	rol    r14d,0x2
    1f:	c1 c3 02             	rol    ebx,0x2
    22:	c1 c1 02             	rol    ecx,0x2
    25:	c1 c2 02             	rol    edx,0x2
    28:	c1 c0 02             	rol    eax,0x2
    2b:	c1 c7 02             	rol    edi,0x2
    2e:	c1 c6 02             	rol    esi,0x2
    31:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.23
  • APERF: 4.73
  • UOPS: 15.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With additional dependency-breaking instructions (before each instruction)

With unroll_count=100 and no inner loop

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
    1c:	4d 85 ff             	test   r15,r15
    1f:	41 c1 c4 02          	rol    r12d,0x2
    23:	4d 85 ff             	test   r15,r15
    26:	41 c1 c5 02          	rol    r13d,0x2
    2a:	4d 85 ff             	test   r15,r15
    2d:	41 c1 c6 02          	rol    r14d,0x2
    31:	4d 85 ff             	test   r15,r15
    34:	c1 c3 02             	rol    ebx,0x2
    37:	4d 85 ff             	test   r15,r15
    3a:	c1 c1 02             	rol    ecx,0x2
    3d:	4d 85 ff             	test   r15,r15
    40:	c1 c2 02             	rol    edx,0x2
    43:	4d 85 ff             	test   r15,r15
    46:	c1 c0 02             	rol    eax,0x2
    49:	4d 85 ff             	test   r15,r15
    4c:	c1 c7 02             	rol    edi,0x2
    4f:	4d 85 ff             	test   r15,r15
    52:	c1 c6 02             	rol    esi,0x2
    55:	4d 85 ff             	test   r15,r15
    58:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 4.81
  • APERF: 7.0
  • UOPS: 28.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
    1c:	4d 85 ff             	test   r15,r15
    1f:	41 c1 c4 02          	rol    r12d,0x2
    23:	4d 85 ff             	test   r15,r15
    26:	41 c1 c5 02          	rol    r13d,0x2
    2a:	4d 85 ff             	test   r15,r15
    2d:	41 c1 c6 02          	rol    r14d,0x2
    31:	4d 85 ff             	test   r15,r15
    34:	c1 c3 02             	rol    ebx,0x2
    37:	4d 85 ff             	test   r15,r15
    3a:	c1 c1 02             	rol    ecx,0x2
    3d:	4d 85 ff             	test   r15,r15
    40:	c1 c2 02             	rol    edx,0x2
    43:	4d 85 ff             	test   r15,r15
    46:	c1 c0 02             	rol    eax,0x2
    49:	4d 85 ff             	test   r15,r15
    4c:	c1 c7 02             	rol    edi,0x2
    4f:	4d 85 ff             	test   r15,r15
    52:	c1 c6 02             	rol    esi,0x2
    55:	4d 85 ff             	test   r15,r15
    58:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.91
  • APERF: 5.72
  • UOPS: 29.0
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	4d 85 ff             	test   r15,r15
     3:	41 c1 c0 02          	rol    r8d,0x2
     7:	4d 85 ff             	test   r15,r15
     a:	41 c1 c1 02          	rol    r9d,0x2
     e:	4d 85 ff             	test   r15,r15
    11:	41 c1 c2 02          	rol    r10d,0x2
    15:	4d 85 ff             	test   r15,r15
    18:	41 c1 c3 02          	rol    r11d,0x2
    1c:	4d 85 ff             	test   r15,r15
    1f:	41 c1 c4 02          	rol    r12d,0x2
    23:	4d 85 ff             	test   r15,r15
    26:	41 c1 c5 02          	rol    r13d,0x2
    2a:	4d 85 ff             	test   r15,r15
    2d:	41 c1 c6 02          	rol    r14d,0x2
    31:	4d 85 ff             	test   r15,r15
    34:	c1 c3 02             	rol    ebx,0x2
    37:	4d 85 ff             	test   r15,r15
    3a:	c1 c1 02             	rol    ecx,0x2
    3d:	4d 85 ff             	test   r15,r15
    40:	c1 c2 02             	rol    edx,0x2
    43:	4d 85 ff             	test   r15,r15
    46:	c1 c0 02             	rol    eax,0x2
    49:	4d 85 ff             	test   r15,r15
    4c:	c1 c7 02             	rol    edi,0x2
    4f:	4d 85 ff             	test   r15,r15
    52:	c1 c6 02             	rol    esi,0x2
    55:	4d 85 ff             	test   r15,r15
    58:	c1 c5 02             	rol    ebp,0x2
  

• Show nanoBench command
• Results:
  • MPERF: 3.4
  • APERF: 4.98
  • UOPS: 28.1
  • FpuPipeAssignment.Total0: 0.0
  • FpuPipeAssignment.Total1: 0.0
  • FpuPipeAssignment.Total2: 0.0
  • FpuPipeAssignment.Total3: 0.0
  • FpuPipeAssignment.Total4: 0.0
  • FpuPipeAssignment.Total5: 0.0
  • DIV_CYCLES: 0.0