VPCOMPRESSB (YMM, YMM) - Throughput and Uops

With unroll_count=500 and no inner loop

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 2.0
  • Reference cycles: 1.04
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 2.0
  • UOPS_MITE: 2.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 1 NOP

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 2.0
  • Reference cycles: 1.04
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 3.0
  • UOPS_MITE: 3.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 2 NOPs

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	90                   	nop
     7:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 2.0
  • Reference cycles: 1.01
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 4.0
  • UOPS_MITE: 4.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 3 NOPs

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	90                   	nop
     7:	90                   	nop
     8:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 2.0
  • Reference cycles: 0.97
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 5.0
  • UOPS_MITE: 4.99
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 4 NOPs

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	90                   	nop
     7:	90                   	nop
     8:	90                   	nop
     9:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 2.0
  • Reference cycles: 0.97
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 6.0
  • UOPS_MITE: 6.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 2.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 2.0
  • Reference cycles: 0.99
  • UOPS_EXECUTED.THREAD: 2.1
  • RETIRE_SLOTS: 2.1
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=100

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 2.0
  • Reference cycles: 1.0
  • UOPS_EXECUTED.THREAD: 2.01
  • RETIRE_SLOTS: 2.01
  • UOPS_MITE: 0.02
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.01
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With unroll_count=200 and no inner loop

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 8.0
  • Reference cycles: 3.99
  • UOPS_EXECUTED.THREAD: 8.0
  • RETIRE_SLOTS: 8.0
  • UOPS_MITE: 8.02
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 8.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 8.01
  • Reference cycles: 4.0
  • UOPS_EXECUTED.THREAD: 8.5
  • RETIRE_SLOTS: 8.5
  • UOPS_MITE: 0.01
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 8.0
  • UOPS_PORT_6: 0.5
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With loop_count=100 and unroll_count=20

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 8.01
  • Reference cycles: 3.97
  • UOPS_EXECUTED.THREAD: 8.05
  • RETIRE_SLOTS: 8.05
  • UOPS_MITE: 0.08
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 8.0
  • UOPS_PORT_6: 0.05
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.04

With unroll_count=100 and no inner loop

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
    18:	62 f2 7d 28 63 cd    	vpcompressb ymm5,ymm1
    1e:	62 f2 7d 28 63 ce    	vpcompressb ymm6,ymm1
    24:	62 f2 7d 28 63 cf    	vpcompressb ymm7,ymm1
    2a:	62 d2 7d 28 63 c8    	vpcompressb ymm8,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 16.0
  • Reference cycles: 7.97
  • UOPS_EXECUTED.THREAD: 16.0
  • RETIRE_SLOTS: 16.0
  • UOPS_MITE: 15.99
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 16.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 8.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
    18:	62 f2 7d 28 63 cd    	vpcompressb ymm5,ymm1
    1e:	62 f2 7d 28 63 ce    	vpcompressb ymm6,ymm1
    24:	62 f2 7d 28 63 cf    	vpcompressb ymm7,ymm1
    2a:	62 d2 7d 28 63 c8    	vpcompressb ymm8,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 16.01
  • Reference cycles: 8.03
  • UOPS_EXECUTED.THREAD: 17.0
  • RETIRE_SLOTS: 17.0
  • UOPS_MITE: 0.01
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 16.0
  • UOPS_PORT_6: 1.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With loop_count=100 and unroll_count=10

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
    18:	62 f2 7d 28 63 cd    	vpcompressb ymm5,ymm1
    1e:	62 f2 7d 28 63 ce    	vpcompressb ymm6,ymm1
    24:	62 f2 7d 28 63 cf    	vpcompressb ymm7,ymm1
    2a:	62 d2 7d 28 63 c8    	vpcompressb ymm8,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 8.2
  • Core cycles: 16.01
  • Reference cycles: 7.99
  • UOPS_EXECUTED.THREAD: 16.1
  • RETIRE_SLOTS: 16.11
  • UOPS_MITE: 0.16
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 16.0
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.08

With unroll_count=100 and no inner loop

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
    18:	62 f2 7d 28 63 cd    	vpcompressb ymm5,ymm1
    1e:	62 f2 7d 28 63 ce    	vpcompressb ymm6,ymm1
    24:	62 f2 7d 28 63 cf    	vpcompressb ymm7,ymm1
    2a:	62 d2 7d 28 63 c8    	vpcompressb ymm8,ymm1
    30:	62 d2 7d 28 63 c9    	vpcompressb ymm9,ymm1
    36:	62 d2 7d 28 63 ca    	vpcompressb ymm10,ymm1
    3c:	62 d2 7d 28 63 cb    	vpcompressb ymm11,ymm1
    42:	62 d2 7d 28 63 cc    	vpcompressb ymm12,ymm1
    48:	62 b2 7d 28 63 c8    	vpcompressb ymm16,ymm1
    4e:	62 b2 7d 28 63 c9    	vpcompressb ymm17,ymm1
    54:	62 b2 7d 28 63 ca    	vpcompressb ymm18,ymm1
    5a:	62 b2 7d 28 63 cb    	vpcompressb ymm19,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 16.0
  • Core cycles: 31.99
  • Reference cycles: 16.47
  • UOPS_EXECUTED.THREAD: 32.0
  • RETIRE_SLOTS: 32.0
  • UOPS_MITE: 31.98
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 32.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 16.0

With loop_count=1000 and unroll_count=1

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
    18:	62 f2 7d 28 63 cd    	vpcompressb ymm5,ymm1
    1e:	62 f2 7d 28 63 ce    	vpcompressb ymm6,ymm1
    24:	62 f2 7d 28 63 cf    	vpcompressb ymm7,ymm1
    2a:	62 d2 7d 28 63 c8    	vpcompressb ymm8,ymm1
    30:	62 d2 7d 28 63 c9    	vpcompressb ymm9,ymm1
    36:	62 d2 7d 28 63 ca    	vpcompressb ymm10,ymm1
    3c:	62 d2 7d 28 63 cb    	vpcompressb ymm11,ymm1
    42:	62 d2 7d 28 63 cc    	vpcompressb ymm12,ymm1
    48:	62 b2 7d 28 63 c8    	vpcompressb ymm16,ymm1
    4e:	62 b2 7d 28 63 c9    	vpcompressb ymm17,ymm1
    54:	62 b2 7d 28 63 ca    	vpcompressb ymm18,ymm1
    5a:	62 b2 7d 28 63 cb    	vpcompressb ymm19,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 18.0
  • Core cycles: 32.01
  • Reference cycles: 15.95
  • UOPS_EXECUTED.THREAD: 33.0
  • RETIRE_SLOTS: 33.01
  • UOPS_MITE: 0.03
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 32.0
  • UOPS_PORT_6: 1.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.02

With loop_count=100 and unroll_count=10

• Code:

     0:	62 f2 7d 28 63 c8    	vpcompressb ymm0,ymm1
     6:	62 f2 7d 28 63 ca    	vpcompressb ymm2,ymm1
     c:	62 f2 7d 28 63 cb    	vpcompressb ymm3,ymm1
    12:	62 f2 7d 28 63 cc    	vpcompressb ymm4,ymm1
    18:	62 f2 7d 28 63 cd    	vpcompressb ymm5,ymm1
    1e:	62 f2 7d 28 63 ce    	vpcompressb ymm6,ymm1
    24:	62 f2 7d 28 63 cf    	vpcompressb ymm7,ymm1
    2a:	62 d2 7d 28 63 c8    	vpcompressb ymm8,ymm1
    30:	62 d2 7d 28 63 c9    	vpcompressb ymm9,ymm1
    36:	62 d2 7d 28 63 ca    	vpcompressb ymm10,ymm1
    3c:	62 d2 7d 28 63 cb    	vpcompressb ymm11,ymm1
    42:	62 d2 7d 28 63 cc    	vpcompressb ymm12,ymm1
    48:	62 b2 7d 28 63 c8    	vpcompressb ymm16,ymm1
    4e:	62 b2 7d 28 63 c9    	vpcompressb ymm17,ymm1
    54:	62 b2 7d 28 63 ca    	vpcompressb ymm18,ymm1
    5a:	62 b2 7d 28 63 cb    	vpcompressb ymm19,ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1

• Show nanoBench command
• Results:
  • Instructions retired: 16.2
  • Core cycles: 32.01
  • Reference cycles: 15.96
  • UOPS_EXECUTED.THREAD: 32.1
  • RETIRE_SLOTS: 32.1
  • UOPS_MITE: 0.32
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 32.0
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.16

With unroll_count=500 and no inner loop

• Code:

     0:	62 f2 7d 28 63 c0    	vpcompressb ymm0,ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 3.0
  • Reference cycles: 1.46
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 2.0
  • UOPS_MITE: 2.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 1 NOP

• Code:

     0:	62 f2 7d 28 63 c0    	vpcompressb ymm0,ymm0
     6:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 3.0
  • Reference cycles: 1.46
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 3.0
  • UOPS_MITE: 3.01
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 2 NOPs

• Code:

     0:	62 f2 7d 28 63 c0    	vpcompressb ymm0,ymm0
     6:	90                   	nop
     7:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 3.0
  • Reference cycles: 1.49
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 4.0
  • UOPS_MITE: 4.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 3 NOPs

• Code:

     0:	62 f2 7d 28 63 c0    	vpcompressb ymm0,ymm0
     6:	90                   	nop
     7:	90                   	nop
     8:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 3.0
  • Reference cycles: 1.46
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 5.0
  • UOPS_MITE: 4.99
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 4 NOPs

• Code:

     0:	62 f2 7d 28 63 c0    	vpcompressb ymm0,ymm0
     6:	90                   	nop
     7:	90                   	nop
     8:	90                   	nop
     9:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 3.0
  • Reference cycles: 1.46
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 6.0
  • UOPS_MITE: 6.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 2.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	62 f2 7d 28 63 c0    	vpcompressb ymm0,ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 3.0
  • Reference cycles: 1.5
  • UOPS_EXECUTED.THREAD: 2.1
  • RETIRE_SLOTS: 2.1
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=100

• Code:

     0:	62 f2 7d 28 63 c0    	vpcompressb ymm0,ymm0
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM0, YMM0, YMM0

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 3.0
  • Reference cycles: 1.5
  • UOPS_EXECUTED.THREAD: 2.01
  • RETIRE_SLOTS: 2.01
  • UOPS_MITE: 0.02
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.0
  • UOPS_PORT_1: 0.0
  • UOPS_PORT_5: 2.0
  • UOPS_PORT_6: 0.01
  • UOPS_PORT_23: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01