VMASKMOVPD (M256, YMM, YMM)

With unroll_count=500 and no inner loop

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 1.0
- Core cycles: 2.0
- Reference cycles: 2.08
- UOPS_RETIRED.ALL: 2.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 1.2
- Core cycles: 2.0
- Reference cycles: 2.05
- UOPS_RETIRED.ALL: 2.2
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 1.02
- Core cycles: 2.0
- Reference cycles: 2.05
- UOPS_RETIRED.ALL: 2.02
- UOPS_MS: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 4.0
- Core cycles: 8.0
- Reference cycles: 7.92
- UOPS_RETIRED.ALL: 8.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 5.0
- Core cycles: 8.01
- Reference cycles: 8.19
- UOPS_RETIRED.ALL: 9.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 4.1
- Core cycles: 8.01
- Reference cycles: 8.2
- UOPS_RETIRED.ALL: 8.1
- UOPS_MS: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1
  17:	c4 c2 7d 2f 8e 80 00 	vmaskmovpd YMMWORD PTR [r14+0x80],ymm0,ymm1
  1e:	00 00 
  20:	c4 c2 7d 2f 8e a0 00 	vmaskmovpd YMMWORD PTR [r14+0xa0],ymm0,ymm1
  27:	00 00 
  29:	c4 c2 7d 2f 8e c0 00 	vmaskmovpd YMMWORD PTR [r14+0xc0],ymm0,ymm1
  30:	00 00 
  32:	c4 c2 7d 2f 8e e0 00 	vmaskmovpd YMMWORD PTR [r14+0xe0],ymm0,ymm1
  39:	00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 8.0
- Core cycles: 16.0
- Reference cycles: 16.8
- UOPS_RETIRED.ALL: 16.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1
  17:	c4 c2 7d 2f 8e 80 00 	vmaskmovpd YMMWORD PTR [r14+0x80],ymm0,ymm1
  1e:	00 00 
  20:	c4 c2 7d 2f 8e a0 00 	vmaskmovpd YMMWORD PTR [r14+0xa0],ymm0,ymm1
  27:	00 00 
  29:	c4 c2 7d 2f 8e c0 00 	vmaskmovpd YMMWORD PTR [r14+0xc0],ymm0,ymm1
  30:	00 00 
  32:	c4 c2 7d 2f 8e e0 00 	vmaskmovpd YMMWORD PTR [r14+0xe0],ymm0,ymm1
  39:	00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 10.0
- Core cycles: 16.02
- Reference cycles: 16.38
- UOPS_RETIRED.ALL: 18.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1
  17:	c4 c2 7d 2f 8e 80 00 	vmaskmovpd YMMWORD PTR [r14+0x80],ymm0,ymm1
  1e:	00 00 
  20:	c4 c2 7d 2f 8e a0 00 	vmaskmovpd YMMWORD PTR [r14+0xa0],ymm0,ymm1
  27:	00 00 
  29:	c4 c2 7d 2f 8e c0 00 	vmaskmovpd YMMWORD PTR [r14+0xc0],ymm0,ymm1
  30:	00 00 
  32:	c4 c2 7d 2f 8e e0 00 	vmaskmovpd YMMWORD PTR [r14+0xe0],ymm0,ymm1
  39:	00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 8.2
- Core cycles: 16.02
- Reference cycles: 16.42
- UOPS_RETIRED.ALL: 16.2
- UOPS_MS: 0.0

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1
  17:	c4 c2 7d 2f 8e 80 00 	vmaskmovpd YMMWORD PTR [r14+0x80],ymm0,ymm1
  1e:	00 00 
  20:	c4 c2 7d 2f 8e a0 00 	vmaskmovpd YMMWORD PTR [r14+0xa0],ymm0,ymm1
  27:	00 00 
  29:	c4 c2 7d 2f 8e c0 00 	vmaskmovpd YMMWORD PTR [r14+0xc0],ymm0,ymm1
  30:	00 00 
  32:	c4 c2 7d 2f 8e e0 00 	vmaskmovpd YMMWORD PTR [r14+0xe0],ymm0,ymm1
  39:	00 00 
  3b:	c4 c2 7d 2f 8e 00 01 	vmaskmovpd YMMWORD PTR [r14+0x100],ymm0,ymm1
  42:	00 00 
  44:	c4 c2 7d 2f 8e 20 01 	vmaskmovpd YMMWORD PTR [r14+0x120],ymm0,ymm1
  4b:	00 00 
  4d:	c4 c2 7d 2f 8e 40 01 	vmaskmovpd YMMWORD PTR [r14+0x140],ymm0,ymm1
  54:	00 00 
  56:	c4 c2 7d 2f 8e 60 01 	vmaskmovpd YMMWORD PTR [r14+0x160],ymm0,ymm1
  5d:	00 00 
  5f:	c4 c2 7d 2f 8e 80 01 	vmaskmovpd YMMWORD PTR [r14+0x180],ymm0,ymm1
  66:	00 00 
  68:	c4 c2 7d 2f 8e a0 01 	vmaskmovpd YMMWORD PTR [r14+0x1a0],ymm0,ymm1
  6f:	00 00 
  71:	c4 c2 7d 2f 8e c0 01 	vmaskmovpd YMMWORD PTR [r14+0x1c0],ymm0,ymm1
  78:	00 00 
  7a:	c4 c2 7d 2f 8e e0 01 	vmaskmovpd YMMWORD PTR [r14+0x1e0],ymm0,ymm1
  81:	00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 32.0
- Reference cycles: 32.64
- UOPS_RETIRED.ALL: 32.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1
  17:	c4 c2 7d 2f 8e 80 00 	vmaskmovpd YMMWORD PTR [r14+0x80],ymm0,ymm1
  1e:	00 00 
  20:	c4 c2 7d 2f 8e a0 00 	vmaskmovpd YMMWORD PTR [r14+0xa0],ymm0,ymm1
  27:	00 00 
  29:	c4 c2 7d 2f 8e c0 00 	vmaskmovpd YMMWORD PTR [r14+0xc0],ymm0,ymm1
  30:	00 00 
  32:	c4 c2 7d 2f 8e e0 00 	vmaskmovpd YMMWORD PTR [r14+0xe0],ymm0,ymm1
  39:	00 00 
  3b:	c4 c2 7d 2f 8e 00 01 	vmaskmovpd YMMWORD PTR [r14+0x100],ymm0,ymm1
  42:	00 00 
  44:	c4 c2 7d 2f 8e 20 01 	vmaskmovpd YMMWORD PTR [r14+0x120],ymm0,ymm1
  4b:	00 00 
  4d:	c4 c2 7d 2f 8e 40 01 	vmaskmovpd YMMWORD PTR [r14+0x140],ymm0,ymm1
  54:	00 00 
  56:	c4 c2 7d 2f 8e 60 01 	vmaskmovpd YMMWORD PTR [r14+0x160],ymm0,ymm1
  5d:	00 00 
  5f:	c4 c2 7d 2f 8e 80 01 	vmaskmovpd YMMWORD PTR [r14+0x180],ymm0,ymm1
  66:	00 00 
  68:	c4 c2 7d 2f 8e a0 01 	vmaskmovpd YMMWORD PTR [r14+0x1a0],ymm0,ymm1
  6f:	00 00 
  71:	c4 c2 7d 2f 8e c0 01 	vmaskmovpd YMMWORD PTR [r14+0x1c0],ymm0,ymm1
  78:	00 00 
  7a:	c4 c2 7d 2f 8e e0 01 	vmaskmovpd YMMWORD PTR [r14+0x1e0],ymm0,ymm1
  81:	00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 32.02
- Reference cycles: 32.78
- UOPS_RETIRED.ALL: 34.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 c2 7d 2f 0e       	vmaskmovpd YMMWORD PTR [r14],ymm0,ymm1
   5:	c4 c2 7d 2f 4e 20    	vmaskmovpd YMMWORD PTR [r14+0x20],ymm0,ymm1
   b:	c4 c2 7d 2f 4e 40    	vmaskmovpd YMMWORD PTR [r14+0x40],ymm0,ymm1
  11:	c4 c2 7d 2f 4e 60    	vmaskmovpd YMMWORD PTR [r14+0x60],ymm0,ymm1
  17:	c4 c2 7d 2f 8e 80 00 	vmaskmovpd YMMWORD PTR [r14+0x80],ymm0,ymm1
  1e:	00 00 
  20:	c4 c2 7d 2f 8e a0 00 	vmaskmovpd YMMWORD PTR [r14+0xa0],ymm0,ymm1
  27:	00 00 
  29:	c4 c2 7d 2f 8e c0 00 	vmaskmovpd YMMWORD PTR [r14+0xc0],ymm0,ymm1
  30:	00 00 
  32:	c4 c2 7d 2f 8e e0 00 	vmaskmovpd YMMWORD PTR [r14+0xe0],ymm0,ymm1
  39:	00 00 
  3b:	c4 c2 7d 2f 8e 00 01 	vmaskmovpd YMMWORD PTR [r14+0x100],ymm0,ymm1
  42:	00 00 
  44:	c4 c2 7d 2f 8e 20 01 	vmaskmovpd YMMWORD PTR [r14+0x120],ymm0,ymm1
  4b:	00 00 
  4d:	c4 c2 7d 2f 8e 40 01 	vmaskmovpd YMMWORD PTR [r14+0x140],ymm0,ymm1
  54:	00 00 
  56:	c4 c2 7d 2f 8e 60 01 	vmaskmovpd YMMWORD PTR [r14+0x160],ymm0,ymm1
  5d:	00 00 
  5f:	c4 c2 7d 2f 8e 80 01 	vmaskmovpd YMMWORD PTR [r14+0x180],ymm0,ymm1
  66:	00 00 
  68:	c4 c2 7d 2f 8e a0 01 	vmaskmovpd YMMWORD PTR [r14+0x1a0],ymm0,ymm1
  6f:	00 00 
  71:	c4 c2 7d 2f 8e c0 01 	vmaskmovpd YMMWORD PTR [r14+0x1c0],ymm0,ymm1
  78:	00 00 
  7a:	c4 c2 7d 2f 8e e0 01 	vmaskmovpd YMMWORD PTR [r14+0x1e0],ymm0,ymm1
  81:	00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 16.2
- Core cycles: 32.02
- Reference cycles: 32.82
- UOPS_RETIRED.ALL: 32.2
- UOPS_MS: 0.0

With an indexed addressing mode

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 1.0
- Core cycles: 2.0
- Reference cycles: 2.05
- UOPS_RETIRED.ALL: 2.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 1.2
- Core cycles: 2.0
- Reference cycles: 2.05
- UOPS_RETIRED.ALL: 2.2
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 1.02
- Core cycles: 2.0
- Reference cycles: 2.05
- UOPS_RETIRED.ALL: 2.02
- UOPS_MS: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 4.0
- Core cycles: 8.0
- Reference cycles: 8.24
- UOPS_RETIRED.ALL: 8.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 5.0
- Core cycles: 8.01
- Reference cycles: 8.21
- UOPS_RETIRED.ALL: 9.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1

Init:

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

Show nanoBench command
Results:
- Instructions retired: 4.1
- Core cycles: 8.01
- Reference cycles: 8.21
- UOPS_RETIRED.ALL: 8.1
- UOPS_MS: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1
  1b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x80],ymm0,ymm1
  22:	00 00 00 
  25:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xa0],ymm0,ymm1
  2c:	00 00 00 
  2f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xc0],ymm0,ymm1
  36:	00 00 00 
  39:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xe0],ymm0,ymm1
  40:	00 00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 8.0
- Core cycles: 16.0
- Reference cycles: 16.8
- UOPS_RETIRED.ALL: 16.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1
  1b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x80],ymm0,ymm1
  22:	00 00 00 
  25:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xa0],ymm0,ymm1
  2c:	00 00 00 
  2f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xc0],ymm0,ymm1
  36:	00 00 00 
  39:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xe0],ymm0,ymm1
  40:	00 00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 10.0
- Core cycles: 16.02
- Reference cycles: 16.4
- UOPS_RETIRED.ALL: 18.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1
  1b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x80],ymm0,ymm1
  22:	00 00 00 
  25:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xa0],ymm0,ymm1
  2c:	00 00 00 
  2f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xc0],ymm0,ymm1
  36:	00 00 00 
  39:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xe0],ymm0,ymm1
  40:	00 00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 8.2
- Core cycles: 16.02
- Reference cycles: 16.43
- UOPS_RETIRED.ALL: 16.2
- UOPS_MS: 0.0

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1
  1b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x80],ymm0,ymm1
  22:	00 00 00 
  25:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xa0],ymm0,ymm1
  2c:	00 00 00 
  2f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xc0],ymm0,ymm1
  36:	00 00 00 
  39:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xe0],ymm0,ymm1
  40:	00 00 00 
  43:	c4 82 7d 2f 8c 2e 00 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x100],ymm0,ymm1
  4a:	01 00 00 
  4d:	c4 82 7d 2f 8c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x120],ymm0,ymm1
  54:	01 00 00 
  57:	c4 82 7d 2f 8c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x140],ymm0,ymm1
  5e:	01 00 00 
  61:	c4 82 7d 2f 8c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x160],ymm0,ymm1
  68:	01 00 00 
  6b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x180],ymm0,ymm1
  72:	01 00 00 
  75:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1a0],ymm0,ymm1
  7c:	01 00 00 
  7f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1c0],ymm0,ymm1
  86:	01 00 00 
  89:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1e0],ymm0,ymm1
  90:	01 00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 16.0
- Core cycles: 32.0
- Reference cycles: 32.64
- UOPS_RETIRED.ALL: 32.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1
  1b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x80],ymm0,ymm1
  22:	00 00 00 
  25:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xa0],ymm0,ymm1
  2c:	00 00 00 
  2f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xc0],ymm0,ymm1
  36:	00 00 00 
  39:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xe0],ymm0,ymm1
  40:	00 00 00 
  43:	c4 82 7d 2f 8c 2e 00 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x100],ymm0,ymm1
  4a:	01 00 00 
  4d:	c4 82 7d 2f 8c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x120],ymm0,ymm1
  54:	01 00 00 
  57:	c4 82 7d 2f 8c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x140],ymm0,ymm1
  5e:	01 00 00 
  61:	c4 82 7d 2f 8c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x160],ymm0,ymm1
  68:	01 00 00 
  6b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x180],ymm0,ymm1
  72:	01 00 00 
  75:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1a0],ymm0,ymm1
  7c:	01 00 00 
  7f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1c0],ymm0,ymm1
  86:	01 00 00 
  89:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1e0],ymm0,ymm1
  90:	01 00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 18.0
- Core cycles: 32.02
- Reference cycles: 32.78
- UOPS_RETIRED.ALL: 34.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 82 7d 2f 0c 2e    	vmaskmovpd YMMWORD PTR [r14+r13*1],ymm0,ymm1
   6:	c4 82 7d 2f 4c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x20],ymm0,ymm1
   d:	c4 82 7d 2f 4c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x40],ymm0,ymm1
  14:	c4 82 7d 2f 4c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x60],ymm0,ymm1
  1b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x80],ymm0,ymm1
  22:	00 00 00 
  25:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xa0],ymm0,ymm1
  2c:	00 00 00 
  2f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xc0],ymm0,ymm1
  36:	00 00 00 
  39:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0xe0],ymm0,ymm1
  40:	00 00 00 
  43:	c4 82 7d 2f 8c 2e 00 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x100],ymm0,ymm1
  4a:	01 00 00 
  4d:	c4 82 7d 2f 8c 2e 20 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x120],ymm0,ymm1
  54:	01 00 00 
  57:	c4 82 7d 2f 8c 2e 40 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x140],ymm0,ymm1
  5e:	01 00 00 
  61:	c4 82 7d 2f 8c 2e 60 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x160],ymm0,ymm1
  68:	01 00 00 
  6b:	c4 82 7d 2f 8c 2e 80 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x180],ymm0,ymm1
  72:	01 00 00 
  75:	c4 82 7d 2f 8c 2e a0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1a0],ymm0,ymm1
  7c:	01 00 00 
  7f:	c4 82 7d 2f 8c 2e c0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1c0],ymm0,ymm1
  86:	01 00 00 
  89:	c4 82 7d 2f 8c 2e e0 	vmaskmovpd YMMWORD PTR [r14+r13*1+0x1e0],ymm0,ymm1
  90:	01 00 00

Init:

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

Show nanoBench command
Results:
- Instructions retired: 16.2
- Core cycles: 32.02
- Reference cycles: 32.8
- UOPS_RETIRED.ALL: 32.2
- UOPS_MS: 0.0

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

With a non-indexed addressing mode

With 1 independent instruction

With unroll_count=500 and no inner loop

With loop_count=1000 and unroll_count=10

With loop_count=100 and unroll_count=100

With 4 independent instructions

With unroll_count=200 and no inner loop

With loop_count=1000 and unroll_count=2

With loop_count=100 and unroll_count=20

With 8 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10

With 16 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10

With an indexed addressing mode

With 1 independent instruction

With unroll_count=500 and no inner loop

With loop_count=1000 and unroll_count=10

With loop_count=100 and unroll_count=100

With 4 independent instructions

With unroll_count=200 and no inner loop

With loop_count=1000 and unroll_count=2

With loop_count=100 and unroll_count=20

With 8 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10

With 16 independent instructions

With unroll_count=100 and no inner loop

With loop_count=1000 and unroll_count=1

With loop_count=100 and unroll_count=10