VSCALEFPD (ZMM, ZMM, ZMM)

With unroll_count=500 and no inner loop

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.75
- APERF: 2.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.72
- APERF: 2.0
- UOPS: 2.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- 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=100

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 1.72
- APERF: 2.0
- UOPS: 2.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- 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 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 7.05
- APERF: 8.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 6.91
- APERF: 8.01
- UOPS: 8.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- 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=20

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 6.9
- APERF: 8.01
- UOPS: 8.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 4.0
- FpuPipeAssignment.Total3: 4.0
- 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 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2
  18:	62 f2 f5 48 2c f2    	vscalefpd zmm6,zmm1,zmm2
  1e:	62 f2 f5 48 2c fa    	vscalefpd zmm7,zmm1,zmm2
  24:	62 72 f5 48 2c c2    	vscalefpd zmm8,zmm1,zmm2
  2a:	62 72 f5 48 2c ca    	vscalefpd zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 13.63
- APERF: 16.0
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2
  18:	62 f2 f5 48 2c f2    	vscalefpd zmm6,zmm1,zmm2
  1e:	62 f2 f5 48 2c fa    	vscalefpd zmm7,zmm1,zmm2
  24:	62 72 f5 48 2c c2    	vscalefpd zmm8,zmm1,zmm2
  2a:	62 72 f5 48 2c ca    	vscalefpd zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 13.82
- APERF: 16.02
- UOPS: 17.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2
  18:	62 f2 f5 48 2c f2    	vscalefpd zmm6,zmm1,zmm2
  1e:	62 f2 f5 48 2c fa    	vscalefpd zmm7,zmm1,zmm2
  24:	62 72 f5 48 2c c2    	vscalefpd zmm8,zmm1,zmm2
  2a:	62 72 f5 48 2c ca    	vscalefpd zmm9,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 13.82
- APERF: 16.01
- UOPS: 16.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 8.0
- FpuPipeAssignment.Total3: 8.0
- 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 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2
  18:	62 f2 f5 48 2c f2    	vscalefpd zmm6,zmm1,zmm2
  1e:	62 f2 f5 48 2c fa    	vscalefpd zmm7,zmm1,zmm2
  24:	62 72 f5 48 2c c2    	vscalefpd zmm8,zmm1,zmm2
  2a:	62 72 f5 48 2c ca    	vscalefpd zmm9,zmm1,zmm2
  30:	62 72 f5 48 2c d2    	vscalefpd zmm10,zmm1,zmm2
  36:	62 72 f5 48 2c da    	vscalefpd zmm11,zmm1,zmm2
  3c:	62 72 f5 48 2c e2    	vscalefpd zmm12,zmm1,zmm2
  42:	62 e2 f5 48 2c c2    	vscalefpd zmm16,zmm1,zmm2
  48:	62 e2 f5 48 2c ca    	vscalefpd zmm17,zmm1,zmm2
  4e:	62 e2 f5 48 2c d2    	vscalefpd zmm18,zmm1,zmm2
  54:	62 e2 f5 48 2c da    	vscalefpd zmm19,zmm1,zmm2
  5a:	62 e2 f5 48 2c e2    	vscalefpd zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 27.73
- APERF: 32.0
- UOPS: 32.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 16.0
- FpuPipeAssignment.Total3: 16.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2
  18:	62 f2 f5 48 2c f2    	vscalefpd zmm6,zmm1,zmm2
  1e:	62 f2 f5 48 2c fa    	vscalefpd zmm7,zmm1,zmm2
  24:	62 72 f5 48 2c c2    	vscalefpd zmm8,zmm1,zmm2
  2a:	62 72 f5 48 2c ca    	vscalefpd zmm9,zmm1,zmm2
  30:	62 72 f5 48 2c d2    	vscalefpd zmm10,zmm1,zmm2
  36:	62 72 f5 48 2c da    	vscalefpd zmm11,zmm1,zmm2
  3c:	62 72 f5 48 2c e2    	vscalefpd zmm12,zmm1,zmm2
  42:	62 e2 f5 48 2c c2    	vscalefpd zmm16,zmm1,zmm2
  48:	62 e2 f5 48 2c ca    	vscalefpd zmm17,zmm1,zmm2
  4e:	62 e2 f5 48 2c d2    	vscalefpd zmm18,zmm1,zmm2
  54:	62 e2 f5 48 2c da    	vscalefpd zmm19,zmm1,zmm2
  5a:	62 e2 f5 48 2c e2    	vscalefpd zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 27.59
- APERF: 32.01
- UOPS: 33.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 16.0
- FpuPipeAssignment.Total3: 16.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f2 f5 48 2c c2    	vscalefpd zmm0,zmm1,zmm2
   6:	62 f2 f5 48 2c da    	vscalefpd zmm3,zmm1,zmm2
   c:	62 f2 f5 48 2c e2    	vscalefpd zmm4,zmm1,zmm2
  12:	62 f2 f5 48 2c ea    	vscalefpd zmm5,zmm1,zmm2
  18:	62 f2 f5 48 2c f2    	vscalefpd zmm6,zmm1,zmm2
  1e:	62 f2 f5 48 2c fa    	vscalefpd zmm7,zmm1,zmm2
  24:	62 72 f5 48 2c c2    	vscalefpd zmm8,zmm1,zmm2
  2a:	62 72 f5 48 2c ca    	vscalefpd zmm9,zmm1,zmm2
  30:	62 72 f5 48 2c d2    	vscalefpd zmm10,zmm1,zmm2
  36:	62 72 f5 48 2c da    	vscalefpd zmm11,zmm1,zmm2
  3c:	62 72 f5 48 2c e2    	vscalefpd zmm12,zmm1,zmm2
  42:	62 e2 f5 48 2c c2    	vscalefpd zmm16,zmm1,zmm2
  48:	62 e2 f5 48 2c ca    	vscalefpd zmm17,zmm1,zmm2
  4e:	62 e2 f5 48 2c d2    	vscalefpd zmm18,zmm1,zmm2
  54:	62 e2 f5 48 2c da    	vscalefpd zmm19,zmm1,zmm2
  5a:	62 e2 f5 48 2c e2    	vscalefpd zmm20,zmm1,zmm2

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM1, [R14];
VMOVUPD ZMM2, [R14]

Show nanoBench command
Results:
- MPERF: 27.6
- APERF: 32.01
- UOPS: 32.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 16.0
- FpuPipeAssignment.Total3: 16.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With the same register for for different operands

With unroll_count=500 and no inner loop

Code:

   0:	62 f2 fd 48 2c c0    	vscalefpd zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	62 f2 fd 48 2c c0    	vscalefpd zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- UOPS: 2.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- 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=100

Code:

   0:	62 f2 fd 48 2c c0    	vscalefpd zmm0,zmm0,zmm0

Init:

MOV R15, 10000;
L: VADDPS ZMM0, ZMM1, ZMM1;
VADDPS ZMM0, ZMM1, ZMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD ZMM0, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- UOPS: 2.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 1.0
- FpuPipeAssignment.Total3: 1.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VSCALEFPD (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 unroll_count=500 and no inner loop

With loop_count=1000 and unroll_count=10

With loop_count=100 and unroll_count=100