VGATHERQPD (YMM, VSIB_YMM, YMM) - Throughput and Uops

With unroll_count=500 and no inner loop

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14

• Show nanoBench command
• Results:
  • Instructions retired: 1.0
  • Core cycles: 4.0
  • Reference cycles: 3.59
  • UOPS_EXECUTED.THREAD: 5.0
  • RETIRE_SLOTS: 4.0
  • UOPS_MITE: 4.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.33
  • UOPS_PORT_1: 0.67
  • UOPS_PORT_2: 2.0
  • UOPS_PORT_3: 2.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_7: 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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	90                   	nop
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14

• Show nanoBench command
• Results:
  • Instructions retired: 2.0
  • Core cycles: 4.0
  • Reference cycles: 3.64
  • UOPS_EXECUTED.THREAD: 5.0
  • RETIRE_SLOTS: 5.0
  • UOPS_MITE: 5.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.67
  • UOPS_PORT_1: 0.33
  • UOPS_PORT_2: 2.0
  • UOPS_PORT_3: 2.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_7: 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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],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;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14

• Show nanoBench command
• Results:
  • Instructions retired: 3.0
  • Core cycles: 4.0
  • Reference cycles: 3.68
  • UOPS_EXECUTED.THREAD: 5.0
  • RETIRE_SLOTS: 6.0
  • UOPS_MITE: 6.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.67
  • UOPS_PORT_1: 0.33
  • UOPS_PORT_2: 2.0
  • UOPS_PORT_3: 2.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_7: 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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14

• Show nanoBench command
• Results:
  • Instructions retired: 1.2
  • Core cycles: 4.0
  • Reference cycles: 3.55
  • UOPS_EXECUTED.THREAD: 5.1
  • RETIRE_SLOTS: 4.1
  • UOPS_MITE: 4.1
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.4
  • UOPS_PORT_1: 0.6
  • UOPS_PORT_2: 2.0
  • UOPS_PORT_3: 2.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=1000, unroll_count=10, and padding (long NOPs)

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
     d:	0f 1f 84 00 00 00 00 
    14:	00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14

• Show nanoBench command
• Results:
  • Instructions retired: 2.2
  • Core cycles: 4.0
  • Reference cycles: 3.55
  • UOPS_EXECUTED.THREAD: 5.1
  • RETIRE_SLOTS: 5.1
  • UOPS_MITE: 0.01
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.67
  • UOPS_PORT_1: 0.33
  • UOPS_PORT_2: 2.0
  • UOPS_PORT_3: 2.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 0.1
  • UOPS_PORT_7: 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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14

• Show nanoBench command
• Results:
  • Instructions retired: 1.02
  • Core cycles: 4.0
  • Reference cycles: 3.56
  • UOPS_EXECUTED.THREAD: 5.01
  • RETIRE_SLOTS: 4.01
  • UOPS_MITE: 4.02
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.34
  • UOPS_PORT_1: 0.66
  • UOPS_PORT_2: 2.0
  • UOPS_PORT_3: 2.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 0.01
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 1.0

With loop_count=100, unroll_count=100, and padding (long NOPs)

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
     d:	0f 1f 84 00 00 00 00 
    14:	00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14

• Show nanoBench command
• Results:
  • Instructions retired: 2.02
  • Core cycles: 4.0
  • Reference cycles: 3.55
  • UOPS_EXECUTED.THREAD: 5.01
  • RETIRE_SLOTS: 5.01
  • UOPS_MITE: 0.05
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 1.67
  • UOPS_PORT_1: 0.33
  • UOPS_PORT_2: 2.0
  • UOPS_PORT_3: 2.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 1.0
  • UOPS_PORT_6: 0.01
  • UOPS_PORT_7: 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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7

• Show nanoBench command
• Results:
  • Instructions retired: 4.0
  • Core cycles: 16.0
  • Reference cycles: 14.19
  • UOPS_EXECUTED.THREAD: 20.0
  • RETIRE_SLOTS: 16.0
  • UOPS_MITE: 16.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 5.34
  • UOPS_PORT_1: 2.67
  • UOPS_PORT_2: 8.0
  • UOPS_PORT_3: 8.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 4.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_7: 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:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7

• Show nanoBench command
• Results:
  • Instructions retired: 5.0
  • Core cycles: 16.01
  • Reference cycles: 14.23
  • UOPS_EXECUTED.THREAD: 20.5
  • RETIRE_SLOTS: 16.5
  • UOPS_MITE: 16.53
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 5.5
  • UOPS_PORT_1: 2.5
  • UOPS_PORT_2: 8.0
  • UOPS_PORT_3: 8.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 4.0
  • UOPS_PORT_6: 0.5
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.01

With loop_count=1000, unroll_count=2, and padding (long NOPs)

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
    1b:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
    22:	0f 1f 84 00 00 00 00 
    29:	00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7

• Show nanoBench command
• Results:
  • Instructions retired: 6.0
  • Core cycles: 16.01
  • Reference cycles: 14.25
  • UOPS_EXECUTED.THREAD: 20.5
  • RETIRE_SLOTS: 17.5
  • UOPS_MITE: 17.52
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 6.0
  • UOPS_PORT_1: 2.01
  • UOPS_PORT_2: 8.0
  • UOPS_PORT_3: 8.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 4.0
  • UOPS_PORT_6: 0.5
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.5

With loop_count=100 and unroll_count=20

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7

• Show nanoBench command
• Results:
  • Instructions retired: 4.1
  • Core cycles: 16.01
  • Reference cycles: 14.24
  • UOPS_EXECUTED.THREAD: 20.05
  • RETIRE_SLOTS: 16.05
  • UOPS_MITE: 16.07
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 5.35
  • UOPS_PORT_1: 2.65
  • UOPS_PORT_2: 8.0
  • UOPS_PORT_3: 8.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 4.0
  • UOPS_PORT_6: 0.05
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.01

With loop_count=100, unroll_count=20, and padding (long NOPs)

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
    1b:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
    22:	0f 1f 84 00 00 00 00 
    29:	00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7

• Show nanoBench command
• Results:
  • Instructions retired: 5.1
  • Core cycles: 16.01
  • Reference cycles: 14.23
  • UOPS_EXECUTED.THREAD: 20.05
  • RETIRE_SLOTS: 17.05
  • UOPS_MITE: 17.08
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 6.0
  • UOPS_PORT_1: 2.0
  • UOPS_PORT_2: 8.0
  • UOPS_PORT_3: 8.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 4.0
  • UOPS_PORT_6: 0.05
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 4.06

With unroll_count=100 and no inner loop

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
    1b:	c4 02 b5 93 44 36 20 	vgatherqpd ymm8,QWORD PTR [r14+ymm14*1+0x20],ymm9
    22:	c4 02 a5 93 54 36 28 	vgatherqpd ymm10,QWORD PTR [r14+ymm14*1+0x28],ymm11
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7;
  VMOVUPD YMM8, [R14];
  MOV [R14+32], RAX;
  VXORPS YMM9, YMM9, YMM9;
  VMOVUPD YMM10, [R14];
  MOV [R14+40], RAX;
  VXORPS YMM11, YMM11, YMM11

• Show nanoBench command
• Results:
  • Instructions retired: 6.0
  • Core cycles: 24.0
  • Reference cycles: 21.28
  • UOPS_EXECUTED.THREAD: 30.0
  • RETIRE_SLOTS: 24.0
  • UOPS_MITE: 24.0
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 8.0
  • UOPS_PORT_1: 4.0
  • UOPS_PORT_2: 12.0
  • UOPS_PORT_3: 12.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 6.0
  • UOPS_PORT_6: 0.0
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 6.0

With loop_count=1000 and unroll_count=2

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
    1b:	c4 02 b5 93 44 36 20 	vgatherqpd ymm8,QWORD PTR [r14+ymm14*1+0x20],ymm9
    22:	c4 02 a5 93 54 36 28 	vgatherqpd ymm10,QWORD PTR [r14+ymm14*1+0x28],ymm11
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7;
  VMOVUPD YMM8, [R14];
  MOV [R14+32], RAX;
  VXORPS YMM9, YMM9, YMM9;
  VMOVUPD YMM10, [R14];
  MOV [R14+40], RAX;
  VXORPS YMM11, YMM11, YMM11

• Show nanoBench command
• Results:
  • Instructions retired: 7.0
  • Core cycles: 24.01
  • Reference cycles: 21.32
  • UOPS_EXECUTED.THREAD: 30.5
  • RETIRE_SLOTS: 24.5
  • UOPS_MITE: 24.53
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 8.0
  • UOPS_PORT_1: 4.0
  • UOPS_PORT_2: 12.0
  • UOPS_PORT_3: 12.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 6.0
  • UOPS_PORT_6: 0.5
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 6.01

With loop_count=1000, unroll_count=2, and padding (long NOPs)

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
    1b:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
    22:	0f 1f 84 00 00 00 00 
    29:	00 
    2a:	c4 02 b5 93 44 36 20 	vgatherqpd ymm8,QWORD PTR [r14+ymm14*1+0x20],ymm9
    31:	c4 02 a5 93 54 36 28 	vgatherqpd ymm10,QWORD PTR [r14+ymm14*1+0x28],ymm11
    38:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
    3f:	0f 1f 84 00 00 00 00 
    46:	00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7;
  VMOVUPD YMM8, [R14];
  MOV [R14+32], RAX;
  VXORPS YMM9, YMM9, YMM9;
  VMOVUPD YMM10, [R14];
  MOV [R14+40], RAX;
  VXORPS YMM11, YMM11, YMM11

• Show nanoBench command
• Results:
  • Instructions retired: 9.0
  • Core cycles: 24.01
  • Reference cycles: 21.36
  • UOPS_EXECUTED.THREAD: 30.5
  • RETIRE_SLOTS: 26.5
  • UOPS_MITE: 26.52
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 9.0
  • UOPS_PORT_1: 3.0
  • UOPS_PORT_2: 12.0
  • UOPS_PORT_3: 12.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 6.0
  • UOPS_PORT_6: 0.5
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 6.51

With loop_count=100 and unroll_count=20

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
    1b:	c4 02 b5 93 44 36 20 	vgatherqpd ymm8,QWORD PTR [r14+ymm14*1+0x20],ymm9
    22:	c4 02 a5 93 54 36 28 	vgatherqpd ymm10,QWORD PTR [r14+ymm14*1+0x28],ymm11
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7;
  VMOVUPD YMM8, [R14];
  MOV [R14+32], RAX;
  VXORPS YMM9, YMM9, YMM9;
  VMOVUPD YMM10, [R14];
  MOV [R14+40], RAX;
  VXORPS YMM11, YMM11, YMM11

• Show nanoBench command
• Results:
  • Instructions retired: 6.1
  • Core cycles: 24.02
  • Reference cycles: 21.34
  • UOPS_EXECUTED.THREAD: 30.05
  • RETIRE_SLOTS: 24.05
  • UOPS_MITE: 24.07
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 8.0
  • UOPS_PORT_1: 4.0
  • UOPS_PORT_2: 12.0
  • UOPS_PORT_3: 12.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 6.0
  • UOPS_PORT_6: 0.05
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 6.01

With loop_count=100, unroll_count=20, and padding (long NOPs)

• Code:

     0:	c4 82 f5 93 04 36    	vgatherqpd ymm0,QWORD PTR [r14+ymm14*1],ymm1
     6:	c4 82 e5 93 54 36 08 	vgatherqpd ymm2,QWORD PTR [r14+ymm14*1+0x8],ymm3
     d:	c4 82 d5 93 64 36 10 	vgatherqpd ymm4,QWORD PTR [r14+ymm14*1+0x10],ymm5
    14:	c4 82 c5 93 74 36 18 	vgatherqpd ymm6,QWORD PTR [r14+ymm14*1+0x18],ymm7
    1b:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
    22:	0f 1f 84 00 00 00 00 
    29:	00 
    2a:	c4 02 b5 93 44 36 20 	vgatherqpd ymm8,QWORD PTR [r14+ymm14*1+0x20],ymm9
    31:	c4 02 a5 93 54 36 28 	vgatherqpd ymm10,QWORD PTR [r14+ymm14*1+0x28],ymm11
    38:	66 66 66 66 66 66 2e 	data16 data16 data16 data16 data16 cs nop WORD PTR [rax+rax*1+0x0]
    3f:	0f 1f 84 00 00 00 00 
    46:	00 
  

• Init:

  MOV R15, 10000;
  L: VADDPS YMM0, YMM1, YMM1;
  VADDPS YMM0, YMM1, YMM1;
  DEC R15;
  JNZ L;
  VZEROALL;
  MOV RAX, 0x4000000040000000;
  MOV [R14+0], RAX;
  MOV [R14+8], RAX;
  MOV [R14+16], RAX;
  MOV [R14+24], RAX;
  VMOVUPD YMM0, [R14];
  VXORPS YMM1, YMM1, YMM1;
  VXORPS YMM14, YMM14, YMM14;
  VMOVUPD YMM2, [R14];
  VXORPS YMM3, YMM3, YMM3;
  VMOVUPD YMM4, [R14];
  VXORPS YMM5, YMM5, YMM5;
  VMOVUPD YMM6, [R14];
  VXORPS YMM7, YMM7, YMM7;
  VMOVUPD YMM8, [R14];
  MOV [R14+32], RAX;
  VXORPS YMM9, YMM9, YMM9;
  VMOVUPD YMM10, [R14];
  MOV [R14+40], RAX;
  VXORPS YMM11, YMM11, YMM11

• Show nanoBench command
• Results:
  • Instructions retired: 8.1
  • Core cycles: 24.01
  • Reference cycles: 21.35
  • UOPS_EXECUTED.THREAD: 30.05
  • RETIRE_SLOTS: 26.05
  • UOPS_MITE: 26.07
  • UOPS_MS: 0.0
  • UOPS_PORT_0: 9.0
  • UOPS_PORT_1: 3.0
  • UOPS_PORT_2: 12.0
  • UOPS_PORT_3: 12.0
  • UOPS_PORT_4: 0.0
  • UOPS_PORT_5: 6.0
  • UOPS_PORT_6: 0.05
  • UOPS_PORT_7: 0.0
  • DIV_CYCLES: 0.0
  • ILD_STALL.LCP: 0.0
  • UOPS_MITE>=1: 6.06