VPADDB (ZMM, ZMM, ZMM)

With unroll_count=500 and no inner loop

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 0.47
- APERF: 0.5
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.25
- FpuPipeAssignment.Total1: 0.24
- FpuPipeAssignment.Total2: 0.25
- FpuPipeAssignment.Total3: 0.26
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.25
- FpuPipeAssignment.Total1: 0.25
- FpuPipeAssignment.Total2: 0.25
- FpuPipeAssignment.Total3: 0.25
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 0.43
- APERF: 0.5
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.25
- FpuPipeAssignment.Total1: 0.25
- FpuPipeAssignment.Total2: 0.25
- FpuPipeAssignment.Total3: 0.25
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 1.72
- APERF: 2.01
- UOPS: 4.0
- FpuPipeAssignment.Total0: 1.01
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.01
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 1.73
- APERF: 2.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 1.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 1.72
- APERF: 2.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 1.0
- FpuPipeAssignment.Total1: 1.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2
  18:	62 f1 75 48 fc f2    	vpaddb zmm6,zmm1,zmm2
  1e:	62 f1 75 48 fc fa    	vpaddb zmm7,zmm1,zmm2
  24:	62 71 75 48 fc c2    	vpaddb zmm8,zmm1,zmm2
  2a:	62 71 75 48 fc ca    	vpaddb zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.07
- UOPS: 8.0
- FpuPipeAssignment.Total0: 2.02
- FpuPipeAssignment.Total1: 1.98
- FpuPipeAssignment.Total2: 1.98
- FpuPipeAssignment.Total3: 2.02
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2
  18:	62 f1 75 48 fc f2    	vpaddb zmm6,zmm1,zmm2
  1e:	62 f1 75 48 fc fa    	vpaddb zmm7,zmm1,zmm2
  24:	62 71 75 48 fc c2    	vpaddb zmm8,zmm1,zmm2
  2a:	62 71 75 48 fc ca    	vpaddb zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.01
- UOPS: 9.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 2.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2
  18:	62 f1 75 48 fc f2    	vpaddb zmm6,zmm1,zmm2
  1e:	62 f1 75 48 fc fa    	vpaddb zmm7,zmm1,zmm2
  24:	62 71 75 48 fc c2    	vpaddb zmm8,zmm1,zmm2
  2a:	62 71 75 48 fc ca    	vpaddb zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 3.46
- APERF: 4.01
- UOPS: 8.1
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 2.0
- FpuPipeAssignment.Total3: 2.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2
  18:	62 f1 75 48 fc f2    	vpaddb zmm6,zmm1,zmm2
  1e:	62 f1 75 48 fc fa    	vpaddb zmm7,zmm1,zmm2
  24:	62 71 75 48 fc c2    	vpaddb zmm8,zmm1,zmm2
  2a:	62 71 75 48 fc ca    	vpaddb zmm9,zmm1,zmm2
  30:	62 71 75 48 fc d2    	vpaddb zmm10,zmm1,zmm2
  36:	62 71 75 48 fc da    	vpaddb zmm11,zmm1,zmm2
  3c:	62 71 75 48 fc e2    	vpaddb zmm12,zmm1,zmm2
  42:	62 e1 75 48 fc c2    	vpaddb zmm16,zmm1,zmm2
  48:	62 e1 75 48 fc ca    	vpaddb zmm17,zmm1,zmm2
  4e:	62 e1 75 48 fc d2    	vpaddb zmm18,zmm1,zmm2
  54:	62 e1 75 48 fc da    	vpaddb zmm19,zmm1,zmm2
  5a:	62 e1 75 48 fc e2    	vpaddb zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 7.05
- APERF: 8.09
- UOPS: 16.0
- FpuPipeAssignment.Total0: 4.03
- FpuPipeAssignment.Total1: 4.03
- FpuPipeAssignment.Total2: 3.97
- FpuPipeAssignment.Total3: 3.97
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2
  18:	62 f1 75 48 fc f2    	vpaddb zmm6,zmm1,zmm2
  1e:	62 f1 75 48 fc fa    	vpaddb zmm7,zmm1,zmm2
  24:	62 71 75 48 fc c2    	vpaddb zmm8,zmm1,zmm2
  2a:	62 71 75 48 fc ca    	vpaddb zmm9,zmm1,zmm2
  30:	62 71 75 48 fc d2    	vpaddb zmm10,zmm1,zmm2
  36:	62 71 75 48 fc da    	vpaddb zmm11,zmm1,zmm2
  3c:	62 71 75 48 fc e2    	vpaddb zmm12,zmm1,zmm2
  42:	62 e1 75 48 fc c2    	vpaddb zmm16,zmm1,zmm2
  48:	62 e1 75 48 fc ca    	vpaddb zmm17,zmm1,zmm2
  4e:	62 e1 75 48 fc d2    	vpaddb zmm18,zmm1,zmm2
  54:	62 e1 75 48 fc da    	vpaddb zmm19,zmm1,zmm2
  5a:	62 e1 75 48 fc e2    	vpaddb zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.01
- UOPS: 17.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f1 75 48 fc c2    	vpaddb zmm0,zmm1,zmm2
   6:	62 f1 75 48 fc da    	vpaddb zmm3,zmm1,zmm2
   c:	62 f1 75 48 fc e2    	vpaddb zmm4,zmm1,zmm2
  12:	62 f1 75 48 fc ea    	vpaddb zmm5,zmm1,zmm2
  18:	62 f1 75 48 fc f2    	vpaddb zmm6,zmm1,zmm2
  1e:	62 f1 75 48 fc fa    	vpaddb zmm7,zmm1,zmm2
  24:	62 71 75 48 fc c2    	vpaddb zmm8,zmm1,zmm2
  2a:	62 71 75 48 fc ca    	vpaddb zmm9,zmm1,zmm2
  30:	62 71 75 48 fc d2    	vpaddb zmm10,zmm1,zmm2
  36:	62 71 75 48 fc da    	vpaddb zmm11,zmm1,zmm2
  3c:	62 71 75 48 fc e2    	vpaddb zmm12,zmm1,zmm2
  42:	62 e1 75 48 fc c2    	vpaddb zmm16,zmm1,zmm2
  48:	62 e1 75 48 fc ca    	vpaddb zmm17,zmm1,zmm2
  4e:	62 e1 75 48 fc d2    	vpaddb zmm18,zmm1,zmm2
  54:	62 e1 75 48 fc da    	vpaddb zmm19,zmm1,zmm2
  5a:	62 e1 75 48 fc e2    	vpaddb zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2

Show nanoBench command
Results:
- MPERF: 6.9
- APERF: 8.01
- UOPS: 16.1
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With the same register for for different operands

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0

Show nanoBench command
Results:
- MPERF: 0.89
- APERF: 1.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.28
- FpuPipeAssignment.Total1: 0.28
- FpuPipeAssignment.Total2: 0.22
- FpuPipeAssignment.Total3: 0.22
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0

Show nanoBench command
Results:
- MPERF: 0.86
- APERF: 1.0
- UOPS: 1.1
- FpuPipeAssignment.Total0: 0.28
- FpuPipeAssignment.Total1: 0.25
- FpuPipeAssignment.Total2: 0.22
- FpuPipeAssignment.Total3: 0.25
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0

Show nanoBench command
Results:
- MPERF: 0.86
- APERF: 1.0
- UOPS: 1.01
- FpuPipeAssignment.Total0: 0.28
- FpuPipeAssignment.Total1: 0.22
- FpuPipeAssignment.Total2: 0.22
- FpuPipeAssignment.Total3: 0.28
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3

Show nanoBench command
Results:
- MPERF: 2.62
- APERF: 3.04
- UOPS: 4.0
- FpuPipeAssignment.Total0: 1.19
- FpuPipeAssignment.Total1: 0.82
- FpuPipeAssignment.Total2: 0.82
- FpuPipeAssignment.Total3: 1.19
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3

Show nanoBench command
Results:
- MPERF: 2.08
- APERF: 2.41
- UOPS: 4.5
- FpuPipeAssignment.Total0: 1.18
- FpuPipeAssignment.Total1: 1.13
- FpuPipeAssignment.Total2: 0.82
- FpuPipeAssignment.Total3: 0.87
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3

Show nanoBench command
Results:
- MPERF: 2.07
- APERF: 2.4
- UOPS: 4.05
- FpuPipeAssignment.Total0: 1.16
- FpuPipeAssignment.Total1: 0.84
- FpuPipeAssignment.Total2: 0.84
- FpuPipeAssignment.Total3: 1.16
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3
  18:	62 f1 5d 48 fc e4    	vpaddb zmm4,zmm4,zmm4
  1e:	62 f1 55 48 fc ed    	vpaddb zmm5,zmm5,zmm5
  24:	62 f1 4d 48 fc f6    	vpaddb zmm6,zmm6,zmm6
  2a:	62 f1 45 48 fc ff    	vpaddb zmm7,zmm7,zmm7

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3;
VXORPS ZMM4, ZMM4, ZMM4;
VXORPS ZMM5, ZMM5, ZMM5;
VXORPS ZMM6, ZMM6, ZMM6;
VXORPS ZMM7, ZMM7, ZMM7

Show nanoBench command
Results:
- MPERF: 3.84
- APERF: 4.39
- UOPS: 8.0
- FpuPipeAssignment.Total0: 2.2
- FpuPipeAssignment.Total1: 2.2
- FpuPipeAssignment.Total2: 1.8
- FpuPipeAssignment.Total3: 1.8
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3
  18:	62 f1 5d 48 fc e4    	vpaddb zmm4,zmm4,zmm4
  1e:	62 f1 55 48 fc ed    	vpaddb zmm5,zmm5,zmm5
  24:	62 f1 4d 48 fc f6    	vpaddb zmm6,zmm6,zmm6
  2a:	62 f1 45 48 fc ff    	vpaddb zmm7,zmm7,zmm7

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3;
VXORPS ZMM4, ZMM4, ZMM4;
VXORPS ZMM5, ZMM5, ZMM5;
VXORPS ZMM6, ZMM6, ZMM6;
VXORPS ZMM7, ZMM7, ZMM7

Show nanoBench command
Results:
- MPERF: 3.83
- APERF: 4.45
- UOPS: 9.0
- FpuPipeAssignment.Total0: 2.22
- FpuPipeAssignment.Total1: 2.22
- FpuPipeAssignment.Total2: 1.78
- FpuPipeAssignment.Total3: 1.78
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3
  18:	62 f1 5d 48 fc e4    	vpaddb zmm4,zmm4,zmm4
  1e:	62 f1 55 48 fc ed    	vpaddb zmm5,zmm5,zmm5
  24:	62 f1 4d 48 fc f6    	vpaddb zmm6,zmm6,zmm6
  2a:	62 f1 45 48 fc ff    	vpaddb zmm7,zmm7,zmm7

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3;
VXORPS ZMM4, ZMM4, ZMM4;
VXORPS ZMM5, ZMM5, ZMM5;
VXORPS ZMM6, ZMM6, ZMM6;
VXORPS ZMM7, ZMM7, ZMM7

Show nanoBench command
Results:
- MPERF: 3.8
- APERF: 4.39
- UOPS: 8.1
- FpuPipeAssignment.Total0: 2.19
- FpuPipeAssignment.Total1: 2.19
- FpuPipeAssignment.Total2: 1.81
- FpuPipeAssignment.Total3: 1.81
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3
  18:	62 f1 5d 48 fc e4    	vpaddb zmm4,zmm4,zmm4
  1e:	62 f1 55 48 fc ed    	vpaddb zmm5,zmm5,zmm5
  24:	62 f1 4d 48 fc f6    	vpaddb zmm6,zmm6,zmm6
  2a:	62 f1 45 48 fc ff    	vpaddb zmm7,zmm7,zmm7
  30:	62 51 3d 48 fc c0    	vpaddb zmm8,zmm8,zmm8
  36:	62 51 35 48 fc c9    	vpaddb zmm9,zmm9,zmm9
  3c:	62 51 2d 48 fc d2    	vpaddb zmm10,zmm10,zmm10
  42:	62 51 25 48 fc db    	vpaddb zmm11,zmm11,zmm11
  48:	62 51 1d 48 fc e4    	vpaddb zmm12,zmm12,zmm12
  4e:	62 a1 7d 40 fc c0    	vpaddb zmm16,zmm16,zmm16
  54:	62 a1 75 40 fc c9    	vpaddb zmm17,zmm17,zmm17
  5a:	62 a1 6d 40 fc d2    	vpaddb zmm18,zmm18,zmm18

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3;
VXORPS ZMM4, ZMM4, ZMM4;
VXORPS ZMM5, ZMM5, ZMM5;
VXORPS ZMM6, ZMM6, ZMM6;
VXORPS ZMM7, ZMM7, ZMM7;
VXORPS ZMM8, ZMM8, ZMM8;
VXORPS ZMM9, ZMM9, ZMM9;
VXORPS ZMM10, ZMM10, ZMM10;
VXORPS ZMM11, ZMM11, ZMM11;
VXORPS ZMM12, ZMM12, ZMM12;
VXORPS ZMM16, ZMM16, ZMM16;
VXORPS ZMM17, ZMM17, ZMM17;
VXORPS ZMM18, ZMM18, ZMM18

Show nanoBench command
Results:
- MPERF: 7.13
- APERF: 8.26
- UOPS: 16.0
- FpuPipeAssignment.Total0: 4.13
- FpuPipeAssignment.Total1: 3.62
- FpuPipeAssignment.Total2: 3.88
- FpuPipeAssignment.Total3: 4.39
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3
  18:	62 f1 5d 48 fc e4    	vpaddb zmm4,zmm4,zmm4
  1e:	62 f1 55 48 fc ed    	vpaddb zmm5,zmm5,zmm5
  24:	62 f1 4d 48 fc f6    	vpaddb zmm6,zmm6,zmm6
  2a:	62 f1 45 48 fc ff    	vpaddb zmm7,zmm7,zmm7
  30:	62 51 3d 48 fc c0    	vpaddb zmm8,zmm8,zmm8
  36:	62 51 35 48 fc c9    	vpaddb zmm9,zmm9,zmm9
  3c:	62 51 2d 48 fc d2    	vpaddb zmm10,zmm10,zmm10
  42:	62 51 25 48 fc db    	vpaddb zmm11,zmm11,zmm11
  48:	62 51 1d 48 fc e4    	vpaddb zmm12,zmm12,zmm12
  4e:	62 a1 7d 40 fc c0    	vpaddb zmm16,zmm16,zmm16
  54:	62 a1 75 40 fc c9    	vpaddb zmm17,zmm17,zmm17
  5a:	62 a1 6d 40 fc d2    	vpaddb zmm18,zmm18,zmm18

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3;
VXORPS ZMM4, ZMM4, ZMM4;
VXORPS ZMM5, ZMM5, ZMM5;
VXORPS ZMM6, ZMM6, ZMM6;
VXORPS ZMM7, ZMM7, ZMM7;
VXORPS ZMM8, ZMM8, ZMM8;
VXORPS ZMM9, ZMM9, ZMM9;
VXORPS ZMM10, ZMM10, ZMM10;
VXORPS ZMM11, ZMM11, ZMM11;
VXORPS ZMM12, ZMM12, ZMM12;
VXORPS ZMM16, ZMM16, ZMM16;
VXORPS ZMM17, ZMM17, ZMM17;
VXORPS ZMM18, ZMM18, ZMM18

Show nanoBench command
Results:
- MPERF: 7.0
- APERF: 8.12
- UOPS: 17.0
- FpuPipeAssignment.Total0: 4.05
- FpuPipeAssignment.Total1: 4.05
- FpuPipeAssignment.Total2: 3.95
- FpuPipeAssignment.Total3: 3.95
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f1 7d 48 fc c0    	vpaddb zmm0,zmm0,zmm0
   6:	62 f1 75 48 fc c9    	vpaddb zmm1,zmm1,zmm1
   c:	62 f1 6d 48 fc d2    	vpaddb zmm2,zmm2,zmm2
  12:	62 f1 65 48 fc db    	vpaddb zmm3,zmm3,zmm3
  18:	62 f1 5d 48 fc e4    	vpaddb zmm4,zmm4,zmm4
  1e:	62 f1 55 48 fc ed    	vpaddb zmm5,zmm5,zmm5
  24:	62 f1 4d 48 fc f6    	vpaddb zmm6,zmm6,zmm6
  2a:	62 f1 45 48 fc ff    	vpaddb zmm7,zmm7,zmm7
  30:	62 51 3d 48 fc c0    	vpaddb zmm8,zmm8,zmm8
  36:	62 51 35 48 fc c9    	vpaddb zmm9,zmm9,zmm9
  3c:	62 51 2d 48 fc d2    	vpaddb zmm10,zmm10,zmm10
  42:	62 51 25 48 fc db    	vpaddb zmm11,zmm11,zmm11
  48:	62 51 1d 48 fc e4    	vpaddb zmm12,zmm12,zmm12
  4e:	62 a1 7d 40 fc c0    	vpaddb zmm16,zmm16,zmm16
  54:	62 a1 75 40 fc c9    	vpaddb zmm17,zmm17,zmm17
  5a:	62 a1 6d 40 fc d2    	vpaddb zmm18,zmm18,zmm18

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS ZMM0, ZMM0, ZMM0;
VXORPS ZMM1, ZMM1, ZMM1;
VXORPS ZMM2, ZMM2, ZMM2;
VXORPS ZMM3, ZMM3, ZMM3;
VXORPS ZMM4, ZMM4, ZMM4;
VXORPS ZMM5, ZMM5, ZMM5;
VXORPS ZMM6, ZMM6, ZMM6;
VXORPS ZMM7, ZMM7, ZMM7;
VXORPS ZMM8, ZMM8, ZMM8;
VXORPS ZMM9, ZMM9, ZMM9;
VXORPS ZMM10, ZMM10, ZMM10;
VXORPS ZMM11, ZMM11, ZMM11;
VXORPS ZMM12, ZMM12, ZMM12;
VXORPS ZMM16, ZMM16, ZMM16;
VXORPS ZMM17, ZMM17, ZMM17;
VXORPS ZMM18, ZMM18, ZMM18

Show nanoBench command
Results:
- MPERF: 7.11
- APERF: 8.25
- UOPS: 16.1
- FpuPipeAssignment.Total0: 4.12
- FpuPipeAssignment.Total1: 3.88
- FpuPipeAssignment.Total2: 3.88
- FpuPipeAssignment.Total3: 4.12
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VPADDB (ZMM, ZMM, ZMM) - 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 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 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 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