VMASKMOVPS (YMM, YMM, M256) - Throughput and Uops

With unroll_count=500 and no inner loop

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 0.93
  • Reference cycles: 0.67
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 2.0
  • UOPS_MITE: 1.98
  • UOPS_MS: 0.11
  • UOPS_PORT_0: 0.34
  • UOPS_PORT_1: 0.34
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.39
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.99

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

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 1.0
  • Reference cycles: 0.8
  • UOPS_EXECUTED.THREAD: 1.99
  • RETIRE_SLOTS: 3.0
  • UOPS_MITE: 2.99
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.31
  • UOPS_PORT_1: 0.32
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • 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:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	90                   	nop
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 1.0
  • Reference cycles: 0.77
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 4.0
  • UOPS_MITE: 4.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.31
  • UOPS_PORT_1: 0.31
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.38
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • 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:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	90                   	nop
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 1.0
  • Reference cycles: 0.8
  • UOPS_EXECUTED.THREAD: 2.01
  • RETIRE_SLOTS: 5.0
  • UOPS_MITE: 5.01
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.31
  • UOPS_PORT_1: 0.32
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • 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:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	90                   	nop
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 1.0
  • Reference cycles: 0.83
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 6.0
  • UOPS_MITE: 6.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.44
  • UOPS_PORT_1: 0.44
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.12
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 5 NOPs

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	90                   	nop
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 6.0
  • Core cycles: 2.0
  • Reference cycles: 1.47
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 7.0
  • UOPS_MITE: 7.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.25
  • UOPS_PORT_1: 0.38
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 2.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 0.51
  • Reference cycles: 0.43
  • UOPS_EXECUTED.THREAD: 2.1
  • RETIRE_SLOTS: 2.1
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.01
  • UOPS_PORT_0: 0.41
  • UOPS_PORT_1: 0.41
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.42
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=100

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 0.53
  • Reference cycles: 0.4
  • UOPS_EXECUTED.THREAD: 2.01
  • RETIRE_SLOTS: 2.01
  • UOPS_MITE: 0.02
  • UOPS_MS: 0.01
  • UOPS_PORT_0: 0.41
  • UOPS_PORT_1: 0.41
  • UOPS_PORT_6: 0.01
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.42
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With unroll_count=200 and no inner loop

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 4.0
  • Reference cycles: 2.96
  • UOPS_EXECUTED.THREAD: 8.0
  • RETIRE_SLOTS: 8.0
  • UOPS_MITE: 8.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.25
  • UOPS_PORT_1: 1.26
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 1.5
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 1.59
  • Reference cycles: 1.32
  • UOPS_EXECUTED.THREAD: 8.51
  • RETIRE_SLOTS: 8.5
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.02
  • UOPS_PORT_0: 1.33
  • UOPS_PORT_1: 1.36
  • UOPS_PORT_6: 0.5
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 1.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 4.01
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=20

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 1.66
  • Reference cycles: 1.27
  • UOPS_EXECUTED.THREAD: 8.05
  • RETIRE_SLOTS: 8.05
  • UOPS_MITE: 0.08
  • UOPS_MS: 0.02
  • UOPS_PORT_0: 1.35
  • UOPS_PORT_1: 1.36
  • UOPS_PORT_6: 0.05
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 1.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.04

With unroll_count=100 and no inner loop

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
    17:	c4 c2 75 2c ae 80 00 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+0x80]
    1e:	00 00 
    20:	c4 c2 75 2c b6 a0 00 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
    27:	00 00 
    29:	c4 c2 75 2c be c0 00 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
    30:	00 00 
    32:	c4 42 75 2c 86 e0 00 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
    39:	00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 7.66
  • Reference cycles: 5.76
  • UOPS_EXECUTED.THREAD: 15.98
  • RETIRE_SLOTS: 15.99
  • UOPS_MITE: 15.74
  • UOPS_MS: 0.36
  • UOPS_PORT_0: 2.52
  • UOPS_PORT_1: 2.55
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 2.97
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 7.88

With loop_count=1000 and unroll_count=1

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
    17:	c4 c2 75 2c ae 80 00 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+0x80]
    1e:	00 00 
    20:	c4 c2 75 2c b6 a0 00 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
    27:	00 00 
    29:	c4 c2 75 2c be c0 00 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
    30:	00 00 
    32:	c4 42 75 2c 86 e0 00 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
    39:	00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 3.15
  • Reference cycles: 2.66
  • UOPS_EXECUTED.THREAD: 17.02
  • RETIRE_SLOTS: 17.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.04
  • UOPS_PORT_0: 2.67
  • UOPS_PORT_1: 2.72
  • UOPS_PORT_6: 1.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 2.75
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 8.01
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
    17:	c4 c2 75 2c ae 80 00 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+0x80]
    1e:	00 00 
    20:	c4 c2 75 2c b6 a0 00 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
    27:	00 00 
    29:	c4 c2 75 2c be c0 00 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
    30:	00 00 
    32:	c4 42 75 2c 86 e0 00 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
    39:	00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 8.2
  • Core cycles: 3.32
  • Reference cycles: 2.59
  • UOPS_EXECUTED.THREAD: 16.1
  • RETIRE_SLOTS: 16.1
  • UOPS_MITE: 0.15
  • UOPS_MS: 0.04
  • UOPS_PORT_0: 2.71
  • UOPS_PORT_1: 2.72
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 2.73
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.07

With unroll_count=100 and no inner loop

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
    17:	c4 c2 75 2c ae 80 00 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+0x80]
    1e:	00 00 
    20:	c4 c2 75 2c b6 a0 00 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
    27:	00 00 
    29:	c4 c2 75 2c be c0 00 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
    30:	00 00 
    32:	c4 42 75 2c 86 e0 00 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
    39:	00 00 
    3b:	c4 42 75 2c 8e 00 01 	vmaskmovps ymm9,ymm1,YMMWORD PTR [r14+0x100]
    42:	00 00 
    44:	c4 42 75 2c 96 20 01 	vmaskmovps ymm10,ymm1,YMMWORD PTR [r14+0x120]
    4b:	00 00 
    4d:	c4 42 75 2c 9e 40 01 	vmaskmovps ymm11,ymm1,YMMWORD PTR [r14+0x140]
    54:	00 00 
    56:	c4 42 75 2c a6 60 01 	vmaskmovps ymm12,ymm1,YMMWORD PTR [r14+0x160]
    5d:	00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX;
  MOV [R14+256], RAX;
  MOV [R14+264], RAX;
  MOV [R14+272], RAX;
  MOV [R14+280], RAX;
  MOV [R14+288], RAX;
  MOV [R14+296], RAX;
  MOV [R14+304], RAX;
  MOV [R14+312], RAX;
  MOV [R14+320], RAX;
  MOV [R14+328], RAX;
  MOV [R14+336], RAX;
  MOV [R14+344], RAX;
  MOV [R14+352], RAX;
  MOV [R14+360], RAX;
  MOV [R14+368], RAX;
  MOV [R14+376], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 12.0
  • Core cycles: 12.0
  • Reference cycles: 9.28
  • UOPS_EXECUTED.THREAD: 23.98
  • RETIRE_SLOTS: 23.99
  • UOPS_MITE: 24.01
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 3.74
  • UOPS_PORT_1: 3.77
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 4.5
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 12.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 11.99

With loop_count=1000 and unroll_count=1

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
    17:	c4 c2 75 2c ae 80 00 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+0x80]
    1e:	00 00 
    20:	c4 c2 75 2c b6 a0 00 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
    27:	00 00 
    29:	c4 c2 75 2c be c0 00 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
    30:	00 00 
    32:	c4 42 75 2c 86 e0 00 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
    39:	00 00 
    3b:	c4 42 75 2c 8e 00 01 	vmaskmovps ymm9,ymm1,YMMWORD PTR [r14+0x100]
    42:	00 00 
    44:	c4 42 75 2c 96 20 01 	vmaskmovps ymm10,ymm1,YMMWORD PTR [r14+0x120]
    4b:	00 00 
    4d:	c4 42 75 2c 9e 40 01 	vmaskmovps ymm11,ymm1,YMMWORD PTR [r14+0x140]
    54:	00 00 
    56:	c4 42 75 2c a6 60 01 	vmaskmovps ymm12,ymm1,YMMWORD PTR [r14+0x160]
    5d:	00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX;
  MOV [R14+256], RAX;
  MOV [R14+264], RAX;
  MOV [R14+272], RAX;
  MOV [R14+280], RAX;
  MOV [R14+288], RAX;
  MOV [R14+296], RAX;
  MOV [R14+304], RAX;
  MOV [R14+312], RAX;
  MOV [R14+320], RAX;
  MOV [R14+328], RAX;
  MOV [R14+336], RAX;
  MOV [R14+344], RAX;
  MOV [R14+352], RAX;
  MOV [R14+360], RAX;
  MOV [R14+368], RAX;
  MOV [R14+376], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 4.98
  • Reference cycles: 3.97
  • UOPS_EXECUTED.THREAD: 25.02
  • RETIRE_SLOTS: 25.01
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.01
  • UOPS_PORT_0: 4.05
  • UOPS_PORT_1: 4.09
  • UOPS_PORT_6: 1.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 4.11
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 12.01
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	c4 c2 75 2c 06       	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14]
     5:	c4 c2 75 2c 56 20    	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+0x20]
     b:	c4 c2 75 2c 5e 40    	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+0x40]
    11:	c4 c2 75 2c 66 60    	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+0x60]
    17:	c4 c2 75 2c ae 80 00 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+0x80]
    1e:	00 00 
    20:	c4 c2 75 2c b6 a0 00 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
    27:	00 00 
    29:	c4 c2 75 2c be c0 00 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
    30:	00 00 
    32:	c4 42 75 2c 86 e0 00 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
    39:	00 00 
    3b:	c4 42 75 2c 8e 00 01 	vmaskmovps ymm9,ymm1,YMMWORD PTR [r14+0x100]
    42:	00 00 
    44:	c4 42 75 2c 96 20 01 	vmaskmovps ymm10,ymm1,YMMWORD PTR [r14+0x120]
    4b:	00 00 
    4d:	c4 42 75 2c 9e 40 01 	vmaskmovps ymm11,ymm1,YMMWORD PTR [r14+0x140]
    54:	00 00 
    56:	c4 42 75 2c a6 60 01 	vmaskmovps ymm12,ymm1,YMMWORD PTR [r14+0x160]
    5d:	00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX;
  MOV [R14+256], RAX;
  MOV [R14+264], RAX;
  MOV [R14+272], RAX;
  MOV [R14+280], RAX;
  MOV [R14+288], RAX;
  MOV [R14+296], RAX;
  MOV [R14+304], RAX;
  MOV [R14+312], RAX;
  MOV [R14+320], RAX;
  MOV [R14+328], RAX;
  MOV [R14+336], RAX;
  MOV [R14+344], RAX;
  MOV [R14+352], RAX;
  MOV [R14+360], RAX;
  MOV [R14+368], RAX;
  MOV [R14+376], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 12.2
  • Core cycles: 4.97
  • Reference cycles: 3.79
  • UOPS_EXECUTED.THREAD: 24.1
  • RETIRE_SLOTS: 24.1
  • UOPS_MITE: 0.21
  • UOPS_MS: 0.03
  • UOPS_PORT_0: 4.04
  • UOPS_PORT_1: 4.06
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 4.09
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 12.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.11

With unroll_count=500 and no inner loop

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 1.0
  • Reference cycles: 0.74
  • UOPS_EXECUTED.THREAD: 1.99
  • RETIRE_SLOTS: 2.0
  • UOPS_MITE: 1.99
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.31
  • UOPS_PORT_1: 0.31
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.38
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • 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:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 1.0
  • Reference cycles: 0.7
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 3.0
  • UOPS_MITE: 3.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.31
  • UOPS_PORT_1: 0.32
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • 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:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 1.0
  • Reference cycles: 0.7
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 4.0
  • UOPS_MITE: 3.99
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.31
  • UOPS_PORT_1: 0.31
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.38
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • 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:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 1.0
  • Reference cycles: 0.74
  • UOPS_EXECUTED.THREAD: 2.01
  • RETIRE_SLOTS: 5.0
  • UOPS_MITE: 5.06
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.31
  • UOPS_PORT_1: 0.32
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • 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:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 1.0
  • Reference cycles: 0.8
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 6.0
  • UOPS_MITE: 6.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.44
  • UOPS_PORT_1: 0.44
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.12
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With unroll_count=500, no inner loop, and 5 NOPs

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	90                   	nop
     7:	90                   	nop
     8:	90                   	nop
     9:	90                   	nop
     a:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 6.0
  • Core cycles: 2.0
  • Reference cycles: 1.44
  • UOPS_EXECUTED.THREAD: 2.0
  • RETIRE_SLOTS: 7.0
  • UOPS_MITE: 7.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 0.25
  • UOPS_PORT_1: 0.38
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 2.0

With loop_count=1000 and unroll_count=10

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 0.51
  • Reference cycles: 0.43
  • UOPS_EXECUTED.THREAD: 2.1
  • RETIRE_SLOTS: 2.1
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.01
  • UOPS_PORT_0: 0.41
  • UOPS_PORT_1: 0.41
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.42
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=100

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 0.52
  • Reference cycles: 0.4
  • UOPS_EXECUTED.THREAD: 2.01
  • RETIRE_SLOTS: 2.01
  • UOPS_MITE: 0.02
  • UOPS_MS: 0.01
  • UOPS_PORT_0: 0.41
  • UOPS_PORT_1: 0.41
  • UOPS_PORT_6: 0.01
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 0.42
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 1.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With unroll_count=200 and no inner loop

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 4.0
  • Reference cycles: 2.88
  • UOPS_EXECUTED.THREAD: 8.0
  • RETIRE_SLOTS: 8.0
  • UOPS_MITE: 7.85
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.25
  • UOPS_PORT_1: 1.25
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 1.5
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 1.56
  • Reference cycles: 1.3
  • UOPS_EXECUTED.THREAD: 8.51
  • RETIRE_SLOTS: 8.5
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.02
  • UOPS_PORT_0: 1.34
  • UOPS_PORT_1: 1.37
  • UOPS_PORT_6: 0.5
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 1.38
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=20

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 1.66
  • Reference cycles: 1.25
  • UOPS_EXECUTED.THREAD: 8.05
  • RETIRE_SLOTS: 8.05
  • UOPS_MITE: 0.09
  • UOPS_MS: 0.02
  • UOPS_PORT_0: 1.35
  • UOPS_PORT_1: 1.36
  • UOPS_PORT_6: 0.05
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 1.37
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 4.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.04

With unroll_count=100 and no inner loop

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
    1b:	c4 82 75 2c ac 2e 80 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
    22:	00 00 00 
    25:	c4 82 75 2c b4 2e a0 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
    2c:	00 00 00 
    2f:	c4 82 75 2c bc 2e c0 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
    36:	00 00 00 
    39:	c4 02 75 2c 84 2e e0 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
    40:	00 00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 8.0
  • Core cycles: 8.0
  • Reference cycles: 5.76
  • UOPS_EXECUTED.THREAD: 15.99
  • RETIRE_SLOTS: 16.0
  • UOPS_MITE: 16.01
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 2.5
  • UOPS_PORT_1: 2.51
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 3.01
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 7.99

With loop_count=1000 and unroll_count=1

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
    1b:	c4 82 75 2c ac 2e 80 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
    22:	00 00 00 
    25:	c4 82 75 2c b4 2e a0 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
    2c:	00 00 00 
    2f:	c4 82 75 2c bc 2e c0 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
    36:	00 00 00 
    39:	c4 02 75 2c 84 2e e0 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
    40:	00 00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 10.0
  • Core cycles: 3.38
  • Reference cycles: 2.85
  • UOPS_EXECUTED.THREAD: 17.01
  • RETIRE_SLOTS: 17.0
  • UOPS_MITE: 0.01
  • UOPS_MS: 0.04
  • UOPS_PORT_0: 2.69
  • UOPS_PORT_1: 2.71
  • UOPS_PORT_6: 1.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 2.73
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 8.02
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.01

With loop_count=100 and unroll_count=10

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
    1b:	c4 82 75 2c ac 2e 80 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
    22:	00 00 00 
    25:	c4 82 75 2c b4 2e a0 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
    2c:	00 00 00 
    2f:	c4 82 75 2c bc 2e c0 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
    36:	00 00 00 
    39:	c4 02 75 2c 84 2e e0 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
    40:	00 00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 8.2
  • Core cycles: 3.34
  • Reference cycles: 2.61
  • UOPS_EXECUTED.THREAD: 16.1
  • RETIRE_SLOTS: 16.11
  • UOPS_MITE: 0.14
  • UOPS_MS: 0.01
  • UOPS_PORT_0: 2.71
  • UOPS_PORT_1: 2.71
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 2.72
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 8.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.07

With unroll_count=100 and no inner loop

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
    1b:	c4 82 75 2c ac 2e 80 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
    22:	00 00 00 
    25:	c4 82 75 2c b4 2e a0 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
    2c:	00 00 00 
    2f:	c4 82 75 2c bc 2e c0 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
    36:	00 00 00 
    39:	c4 02 75 2c 84 2e e0 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
    40:	00 00 00 
    43:	c4 02 75 2c 8c 2e 00 	vmaskmovps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100]
    4a:	01 00 00 
    4d:	c4 02 75 2c 94 2e 20 	vmaskmovps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120]
    54:	01 00 00 
    57:	c4 02 75 2c 9c 2e 40 	vmaskmovps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140]
    5e:	01 00 00 
    61:	c4 02 75 2c a4 2e 60 	vmaskmovps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160]
    68:	01 00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX;
  MOV [R14+256], RAX;
  MOV [R14+264], RAX;
  MOV [R14+272], RAX;
  MOV [R14+280], RAX;
  MOV [R14+288], RAX;
  MOV [R14+296], RAX;
  MOV [R14+304], RAX;
  MOV [R14+312], RAX;
  MOV [R14+320], RAX;
  MOV [R14+328], RAX;
  MOV [R14+336], RAX;
  MOV [R14+344], RAX;
  MOV [R14+352], RAX;
  MOV [R14+360], RAX;
  MOV [R14+368], RAX;
  MOV [R14+376], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 12.0
  • Core cycles: 12.0
  • Reference cycles: 8.96
  • UOPS_EXECUTED.THREAD: 24.03
  • RETIRE_SLOTS: 24.01
  • UOPS_MITE: 23.99
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 3.76
  • UOPS_PORT_1: 3.77
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 4.5
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 12.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 12.02

With loop_count=1000 and unroll_count=1

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
    1b:	c4 82 75 2c ac 2e 80 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
    22:	00 00 00 
    25:	c4 82 75 2c b4 2e a0 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
    2c:	00 00 00 
    2f:	c4 82 75 2c bc 2e c0 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
    36:	00 00 00 
    39:	c4 02 75 2c 84 2e e0 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
    40:	00 00 00 
    43:	c4 02 75 2c 8c 2e 00 	vmaskmovps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100]
    4a:	01 00 00 
    4d:	c4 02 75 2c 94 2e 20 	vmaskmovps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120]
    54:	01 00 00 
    57:	c4 02 75 2c 9c 2e 40 	vmaskmovps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140]
    5e:	01 00 00 
    61:	c4 02 75 2c a4 2e 60 	vmaskmovps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160]
    68:	01 00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX;
  MOV [R14+256], RAX;
  MOV [R14+264], RAX;
  MOV [R14+272], RAX;
  MOV [R14+280], RAX;
  MOV [R14+288], RAX;
  MOV [R14+296], RAX;
  MOV [R14+304], RAX;
  MOV [R14+312], RAX;
  MOV [R14+320], RAX;
  MOV [R14+328], RAX;
  MOV [R14+336], RAX;
  MOV [R14+344], RAX;
  MOV [R14+352], RAX;
  MOV [R14+360], RAX;
  MOV [R14+368], RAX;
  MOV [R14+376], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 14.0
  • Core cycles: 4.78
  • Reference cycles: 4.03
  • UOPS_EXECUTED.THREAD: 25.01
  • RETIRE_SLOTS: 25.0
  • UOPS_MITE: 0.0
  • UOPS_MS: 0.03
  • UOPS_PORT_0: 4.03
  • UOPS_PORT_1: 4.08
  • UOPS_PORT_6: 1.0
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 4.12
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 12.01
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.0

With loop_count=100 and unroll_count=10

• Code:

     0:	c4 82 75 2c 04 2e    	vmaskmovps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
     6:	c4 82 75 2c 54 2e 20 	vmaskmovps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
     d:	c4 82 75 2c 5c 2e 40 	vmaskmovps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
    14:	c4 82 75 2c 64 2e 60 	vmaskmovps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
    1b:	c4 82 75 2c ac 2e 80 	vmaskmovps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
    22:	00 00 00 
    25:	c4 82 75 2c b4 2e a0 	vmaskmovps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
    2c:	00 00 00 
    2f:	c4 82 75 2c bc 2e c0 	vmaskmovps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
    36:	00 00 00 
    39:	c4 02 75 2c 84 2e e0 	vmaskmovps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
    40:	00 00 00 
    43:	c4 02 75 2c 8c 2e 00 	vmaskmovps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100]
    4a:	01 00 00 
    4d:	c4 02 75 2c 94 2e 20 	vmaskmovps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120]
    54:	01 00 00 
    57:	c4 02 75 2c 9c 2e 40 	vmaskmovps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140]
    5e:	01 00 00 
    61:	c4 02 75 2c a4 2e 60 	vmaskmovps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160]
    68:	01 00 00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  VXORPS YMM1, YMM1, YMM1;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  XOR R13, R13;
  MOV [R14+32], RAX;
  MOV [R14+40], RAX;
  MOV [R14+48], RAX;
  MOV [R14+56], RAX;
  MOV [R14+64], RAX;
  MOV [R14+72], RAX;
  MOV [R14+80], RAX;
  MOV [R14+88], RAX;
  MOV [R14+96], RAX;
  MOV [R14+104], RAX;
  MOV [R14+112], RAX;
  MOV [R14+120], RAX;
  MOV [R14+128], RAX;
  MOV [R14+136], RAX;
  MOV [R14+144], RAX;
  MOV [R14+152], RAX;
  MOV [R14+160], RAX;
  MOV [R14+168], RAX;
  MOV [R14+176], RAX;
  MOV [R14+184], RAX;
  MOV [R14+192], RAX;
  MOV [R14+200], RAX;
  MOV [R14+208], RAX;
  MOV [R14+216], RAX;
  MOV [R14+224], RAX;
  MOV [R14+232], RAX;
  MOV [R14+240], RAX;
  MOV [R14+248], RAX;
  MOV [R14+256], RAX;
  MOV [R14+264], RAX;
  MOV [R14+272], RAX;
  MOV [R14+280], RAX;
  MOV [R14+288], RAX;
  MOV [R14+296], RAX;
  MOV [R14+304], RAX;
  MOV [R14+312], RAX;
  MOV [R14+320], RAX;
  MOV [R14+328], RAX;
  MOV [R14+336], RAX;
  MOV [R14+344], RAX;
  MOV [R14+352], RAX;
  MOV [R14+360], RAX;
  MOV [R14+368], RAX;
  MOV [R14+376], RAX

• Show nanoBench command
• Results:
  • Instructions retired: 12.2
  • Core cycles: 4.95
  • Reference cycles: 3.81
  • UOPS_EXECUTED.THREAD: 24.1
  • RETIRE_SLOTS: 24.1
  • UOPS_MITE: 0.22
  • UOPS_MS: 0.03
  • UOPS_PORT_0: 4.05
  • UOPS_PORT_1: 4.08
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_49: 0.0
  • UOPS_PORT_78: 0.0
  • UOPS_PORT_5B: 4.09
  • UOPS_PORT_5B>=2: 0.0
  • UOPS_PORT_23A: 12.01
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 0.11