VFMADD132PS (YMM, YMM, YMM)

With unroll_count=500 and no inner loop

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- Instructions retired: 1.0
- Core cycles: 6.0
- Reference cycles: 6.24
- UOPS_RETIRED.ALL: 2.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- Instructions retired: 1.2
- Core cycles: 6.0
- Reference cycles: 6.15
- UOPS_RETIRED.ALL: 2.2
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14]

Show nanoBench command
Results:
- Instructions retired: 1.02
- Core cycles: 6.0
- Reference cycles: 6.15
- UOPS_RETIRED.ALL: 2.02
- UOPS_MS: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14]

Show nanoBench command
Results:
- Instructions retired: 4.0
- Core cycles: 6.0
- Reference cycles: 6.08
- UOPS_RETIRED.ALL: 8.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14]

Show nanoBench command
Results:
- Instructions retired: 5.0
- Core cycles: 6.01
- Reference cycles: 6.16
- UOPS_RETIRED.ALL: 9.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14]

Show nanoBench command
Results:
- Instructions retired: 4.1
- Core cycles: 6.01
- Reference cycles: 6.15
- UOPS_RETIRED.ALL: 8.1
- UOPS_MS: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2
  14:	c4 e2 75 98 f2       	vfmadd132ps ymm6,ymm1,ymm2
  19:	c4 e2 75 98 fa       	vfmadd132ps ymm7,ymm1,ymm2
  1e:	c4 62 75 98 c2       	vfmadd132ps ymm8,ymm1,ymm2
  23:	c4 62 75 98 ca       	vfmadd132ps ymm9,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14]

Show nanoBench command
Results:
- Instructions retired: 8.0
- Core cycles: 8.0
- Reference cycles: 8.32
- UOPS_RETIRED.ALL: 16.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2
  14:	c4 e2 75 98 f2       	vfmadd132ps ymm6,ymm1,ymm2
  19:	c4 e2 75 98 fa       	vfmadd132ps ymm7,ymm1,ymm2
  1e:	c4 62 75 98 c2       	vfmadd132ps ymm8,ymm1,ymm2
  23:	c4 62 75 98 ca       	vfmadd132ps ymm9,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14]

Show nanoBench command
Results:
- Instructions retired: 10.0
- Core cycles: 8.02
- Reference cycles: 8.21
- UOPS_RETIRED.ALL: 18.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2
  14:	c4 e2 75 98 f2       	vfmadd132ps ymm6,ymm1,ymm2
  19:	c4 e2 75 98 fa       	vfmadd132ps ymm7,ymm1,ymm2
  1e:	c4 62 75 98 c2       	vfmadd132ps ymm8,ymm1,ymm2
  23:	c4 62 75 98 ca       	vfmadd132ps ymm9,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14]

Show nanoBench command
Results:
- Instructions retired: 8.2
- Core cycles: 8.02
- Reference cycles: 8.18
- UOPS_RETIRED.ALL: 16.2
- UOPS_MS: 0.0

With 11 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2
  14:	c4 e2 75 98 f2       	vfmadd132ps ymm6,ymm1,ymm2
  19:	c4 e2 75 98 fa       	vfmadd132ps ymm7,ymm1,ymm2
  1e:	c4 62 75 98 c2       	vfmadd132ps ymm8,ymm1,ymm2
  23:	c4 62 75 98 ca       	vfmadd132ps ymm9,ymm1,ymm2
  28:	c4 62 75 98 d2       	vfmadd132ps ymm10,ymm1,ymm2
  2d:	c4 62 75 98 da       	vfmadd132ps ymm11,ymm1,ymm2
  32:	c4 62 75 98 e2       	vfmadd132ps ymm12,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- Instructions retired: 11.0
- Core cycles: 11.01
- Reference cycles: 11.2
- UOPS_RETIRED.ALL: 22.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2
  14:	c4 e2 75 98 f2       	vfmadd132ps ymm6,ymm1,ymm2
  19:	c4 e2 75 98 fa       	vfmadd132ps ymm7,ymm1,ymm2
  1e:	c4 62 75 98 c2       	vfmadd132ps ymm8,ymm1,ymm2
  23:	c4 62 75 98 ca       	vfmadd132ps ymm9,ymm1,ymm2
  28:	c4 62 75 98 d2       	vfmadd132ps ymm10,ymm1,ymm2
  2d:	c4 62 75 98 da       	vfmadd132ps ymm11,ymm1,ymm2
  32:	c4 62 75 98 e2       	vfmadd132ps ymm12,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- Instructions retired: 13.0
- Core cycles: 11.02
- Reference cycles: 11.28
- UOPS_RETIRED.ALL: 24.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 75 98 c2       	vfmadd132ps ymm0,ymm1,ymm2
   5:	c4 e2 75 98 da       	vfmadd132ps ymm3,ymm1,ymm2
   a:	c4 e2 75 98 e2       	vfmadd132ps ymm4,ymm1,ymm2
   f:	c4 e2 75 98 ea       	vfmadd132ps ymm5,ymm1,ymm2
  14:	c4 e2 75 98 f2       	vfmadd132ps ymm6,ymm1,ymm2
  19:	c4 e2 75 98 fa       	vfmadd132ps ymm7,ymm1,ymm2
  1e:	c4 62 75 98 c2       	vfmadd132ps ymm8,ymm1,ymm2
  23:	c4 62 75 98 ca       	vfmadd132ps ymm9,ymm1,ymm2
  28:	c4 62 75 98 d2       	vfmadd132ps ymm10,ymm1,ymm2
  2d:	c4 62 75 98 da       	vfmadd132ps ymm11,ymm1,ymm2
  32:	c4 62 75 98 e2       	vfmadd132ps ymm12,ymm1,ymm2

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- Instructions retired: 11.2
- Core cycles: 11.02
- Reference cycles: 11.23
- UOPS_RETIRED.ALL: 22.2
- UOPS_MS: 0.0

With the same register for for different operands

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0

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]

Show nanoBench command
Results:
- Instructions retired: 1.0
- Core cycles: 6.0
- Reference cycles: 6.14
- UOPS_RETIRED.ALL: 2.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0

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]

Show nanoBench command
Results:
- Instructions retired: 1.2
- Core cycles: 6.0
- Reference cycles: 6.15
- UOPS_RETIRED.ALL: 2.2
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0

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]

Show nanoBench command
Results:
- Instructions retired: 1.02
- Core cycles: 6.0
- Reference cycles: 6.15
- UOPS_RETIRED.ALL: 2.02
- UOPS_MS: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14]

Show nanoBench command
Results:
- Instructions retired: 4.0
- Core cycles: 6.0
- Reference cycles: 6.08
- UOPS_RETIRED.ALL: 8.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14]

Show nanoBench command
Results:
- Instructions retired: 5.0
- Core cycles: 6.01
- Reference cycles: 6.14
- UOPS_RETIRED.ALL: 9.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14]

Show nanoBench command
Results:
- Instructions retired: 4.1
- Core cycles: 6.01
- Reference cycles: 6.18
- UOPS_RETIRED.ALL: 8.1
- UOPS_MS: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3
  14:	c4 e2 5d 98 e4       	vfmadd132ps ymm4,ymm4,ymm4
  19:	c4 e2 55 98 ed       	vfmadd132ps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 98 f6       	vfmadd132ps ymm6,ymm6,ymm6
  23:	c4 e2 45 98 ff       	vfmadd132ps ymm7,ymm7,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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14]

Show nanoBench command
Results:
- Instructions retired: 8.0
- Core cycles: 8.0
- Reference cycles: 8.64
- UOPS_RETIRED.ALL: 16.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3
  14:	c4 e2 5d 98 e4       	vfmadd132ps ymm4,ymm4,ymm4
  19:	c4 e2 55 98 ed       	vfmadd132ps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 98 f6       	vfmadd132ps ymm6,ymm6,ymm6
  23:	c4 e2 45 98 ff       	vfmadd132ps ymm7,ymm7,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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14]

Show nanoBench command
Results:
- Instructions retired: 10.0
- Core cycles: 8.02
- Reference cycles: 8.18
- UOPS_RETIRED.ALL: 18.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3
  14:	c4 e2 5d 98 e4       	vfmadd132ps ymm4,ymm4,ymm4
  19:	c4 e2 55 98 ed       	vfmadd132ps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 98 f6       	vfmadd132ps ymm6,ymm6,ymm6
  23:	c4 e2 45 98 ff       	vfmadd132ps ymm7,ymm7,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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14]

Show nanoBench command
Results:
- Instructions retired: 8.2
- Core cycles: 8.02
- Reference cycles: 8.19
- UOPS_RETIRED.ALL: 16.2
- UOPS_MS: 0.0

With 13 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3
  14:	c4 e2 5d 98 e4       	vfmadd132ps ymm4,ymm4,ymm4
  19:	c4 e2 55 98 ed       	vfmadd132ps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 98 f6       	vfmadd132ps ymm6,ymm6,ymm6
  23:	c4 e2 45 98 ff       	vfmadd132ps ymm7,ymm7,ymm7
  28:	c4 42 3d 98 c0       	vfmadd132ps ymm8,ymm8,ymm8
  2d:	c4 42 35 98 c9       	vfmadd132ps ymm9,ymm9,ymm9
  32:	c4 42 2d 98 d2       	vfmadd132ps ymm10,ymm10,ymm10
  37:	c4 42 25 98 db       	vfmadd132ps ymm11,ymm11,ymm11
  3c:	c4 42 1d 98 e4       	vfmadd132ps ymm12,ymm12,ymm12

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- Instructions retired: 13.0
- Core cycles: 13.0
- Reference cycles: 13.6
- UOPS_RETIRED.ALL: 26.0
- UOPS_MS: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3
  14:	c4 e2 5d 98 e4       	vfmadd132ps ymm4,ymm4,ymm4
  19:	c4 e2 55 98 ed       	vfmadd132ps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 98 f6       	vfmadd132ps ymm6,ymm6,ymm6
  23:	c4 e2 45 98 ff       	vfmadd132ps ymm7,ymm7,ymm7
  28:	c4 42 3d 98 c0       	vfmadd132ps ymm8,ymm8,ymm8
  2d:	c4 42 35 98 c9       	vfmadd132ps ymm9,ymm9,ymm9
  32:	c4 42 2d 98 d2       	vfmadd132ps ymm10,ymm10,ymm10
  37:	c4 42 25 98 db       	vfmadd132ps ymm11,ymm11,ymm11
  3c:	c4 42 1d 98 e4       	vfmadd132ps ymm12,ymm12,ymm12

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- Instructions retired: 15.0
- Core cycles: 13.02
- Reference cycles: 13.39
- UOPS_RETIRED.ALL: 28.0
- UOPS_MS: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 e2 7d 98 c0       	vfmadd132ps ymm0,ymm0,ymm0
   5:	c4 e2 75 98 c9       	vfmadd132ps ymm1,ymm1,ymm1
   a:	c4 e2 6d 98 d2       	vfmadd132ps ymm2,ymm2,ymm2
   f:	c4 e2 65 98 db       	vfmadd132ps ymm3,ymm3,ymm3
  14:	c4 e2 5d 98 e4       	vfmadd132ps ymm4,ymm4,ymm4
  19:	c4 e2 55 98 ed       	vfmadd132ps ymm5,ymm5,ymm5
  1e:	c4 e2 4d 98 f6       	vfmadd132ps ymm6,ymm6,ymm6
  23:	c4 e2 45 98 ff       	vfmadd132ps ymm7,ymm7,ymm7
  28:	c4 42 3d 98 c0       	vfmadd132ps ymm8,ymm8,ymm8
  2d:	c4 42 35 98 c9       	vfmadd132ps ymm9,ymm9,ymm9
  32:	c4 42 2d 98 d2       	vfmadd132ps ymm10,ymm10,ymm10
  37:	c4 42 25 98 db       	vfmadd132ps ymm11,ymm11,ymm11
  3c:	c4 42 1d 98 e4       	vfmadd132ps ymm12,ymm12,ymm12

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];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
VMOVUPD YMM3, [R14];
VMOVUPD YMM4, [R14];
VMOVUPD YMM5, [R14];
VMOVUPD YMM6, [R14];
VMOVUPD YMM7, [R14];
VMOVUPD YMM8, [R14];
VMOVUPD YMM9, [R14];
VMOVUPD YMM10, [R14];
VMOVUPD YMM11, [R14];
VMOVUPD YMM12, [R14]

Show nanoBench command
Results:
- Instructions retired: 13.2
- Core cycles: 13.02
- Reference cycles: 13.36
- UOPS_RETIRED.ALL: 26.2
- UOPS_MS: 0.0

VFMADD132PS (YMM, YMM, YMM) - Throughput and Uops

With different registers for different operands

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 11 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 the same register for for different operands

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 13 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