VZEROUPPER - Throughput and Uops

With unroll_count=500 and no inner loop

• Code:

     0:	c5 f8 77             	vzeroupper
  

• Init:

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

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 1.0
  • Reference cycles: 0.81
  • UOPS_RETIRED.ALL: 1.0
  • UOPS_MS: 0.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	c5 f8 77             	vzeroupper
  

• Init:

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

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 1.0
  • Reference cycles: 0.84
  • UOPS_RETIRED.ALL: 1.2
  • UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

• Code:

     0:	c5 f8 77             	vzeroupper
  

• Init:

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

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 1.01
  • Reference cycles: 0.85
  • UOPS_RETIRED.ALL: 1.02
  • UOPS_MS: 0.0