VEXTRACTF64X4 (YMM, ZMM, I8)

With unroll_count=500 and no inner loop

Code:

   0:	62 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 0.41
- APERF: 0.5
- UOPS: 1.0
- 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=1000 and unroll_count=10

Code:

   0:	62 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2

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]

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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2

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]

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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 1.8
- 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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 1.74
- 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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 1.74
- 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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2
  1c:	62 f3 fd 48 1b cd 02 	vextractf64x4 ymm5,zmm1,0x2
  23:	62 f3 fd 48 1b ce 02 	vextractf64x4 ymm6,zmm1,0x2
  2a:	62 f3 fd 48 1b cf 02 	vextractf64x4 ymm7,zmm1,0x2
  31:	62 d3 fd 48 1b c8 02 	vextractf64x4 ymm8,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 3.53
- APERF: 4.02
- UOPS: 8.0
- FpuPipeAssignment.Total0: 2.01
- FpuPipeAssignment.Total1: 2.01
- FpuPipeAssignment.Total2: 1.99
- FpuPipeAssignment.Total3: 1.99
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2
  1c:	62 f3 fd 48 1b cd 02 	vextractf64x4 ymm5,zmm1,0x2
  23:	62 f3 fd 48 1b ce 02 	vextractf64x4 ymm6,zmm1,0x2
  2a:	62 f3 fd 48 1b cf 02 	vextractf64x4 ymm7,zmm1,0x2
  31:	62 d3 fd 48 1b c8 02 	vextractf64x4 ymm8,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 3.48
- 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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2
  1c:	62 f3 fd 48 1b cd 02 	vextractf64x4 ymm5,zmm1,0x2
  23:	62 f3 fd 48 1b ce 02 	vextractf64x4 ymm6,zmm1,0x2
  2a:	62 f3 fd 48 1b cf 02 	vextractf64x4 ymm7,zmm1,0x2
  31:	62 d3 fd 48 1b c8 02 	vextractf64x4 ymm8,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 3.48
- 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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2
  1c:	62 f3 fd 48 1b cd 02 	vextractf64x4 ymm5,zmm1,0x2
  23:	62 f3 fd 48 1b ce 02 	vextractf64x4 ymm6,zmm1,0x2
  2a:	62 f3 fd 48 1b cf 02 	vextractf64x4 ymm7,zmm1,0x2
  31:	62 d3 fd 48 1b c8 02 	vextractf64x4 ymm8,zmm1,0x2
  38:	62 d3 fd 48 1b c9 02 	vextractf64x4 ymm9,zmm1,0x2
  3f:	62 d3 fd 48 1b ca 02 	vextractf64x4 ymm10,zmm1,0x2
  46:	62 d3 fd 48 1b cb 02 	vextractf64x4 ymm11,zmm1,0x2
  4d:	62 d3 fd 48 1b cc 02 	vextractf64x4 ymm12,zmm1,0x2
  54:	62 b3 fd 48 1b c8 02 	vextractf64x4 ymm16,zmm1,0x2
  5b:	62 b3 fd 48 1b c9 02 	vextractf64x4 ymm17,zmm1,0x2
  62:	62 b3 fd 48 1b ca 02 	vextractf64x4 ymm18,zmm1,0x2
  69:	62 b3 fd 48 1b cb 02 	vextractf64x4 ymm19,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 6.89
- APERF: 7.98
- UOPS: 16.0
- FpuPipeAssignment.Total0: 3.99
- FpuPipeAssignment.Total1: 4.05
- FpuPipeAssignment.Total2: 4.01
- FpuPipeAssignment.Total3: 3.95
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2
  1c:	62 f3 fd 48 1b cd 02 	vextractf64x4 ymm5,zmm1,0x2
  23:	62 f3 fd 48 1b ce 02 	vextractf64x4 ymm6,zmm1,0x2
  2a:	62 f3 fd 48 1b cf 02 	vextractf64x4 ymm7,zmm1,0x2
  31:	62 d3 fd 48 1b c8 02 	vextractf64x4 ymm8,zmm1,0x2
  38:	62 d3 fd 48 1b c9 02 	vextractf64x4 ymm9,zmm1,0x2
  3f:	62 d3 fd 48 1b ca 02 	vextractf64x4 ymm10,zmm1,0x2
  46:	62 d3 fd 48 1b cb 02 	vextractf64x4 ymm11,zmm1,0x2
  4d:	62 d3 fd 48 1b cc 02 	vextractf64x4 ymm12,zmm1,0x2
  54:	62 b3 fd 48 1b c8 02 	vextractf64x4 ymm16,zmm1,0x2
  5b:	62 b3 fd 48 1b c9 02 	vextractf64x4 ymm17,zmm1,0x2
  62:	62 b3 fd 48 1b ca 02 	vextractf64x4 ymm18,zmm1,0x2
  69:	62 b3 fd 48 1b cb 02 	vextractf64x4 ymm19,zmm1,0x2

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]

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 f3 fd 48 1b c8 02 	vextractf64x4 ymm0,zmm1,0x2
   7:	62 f3 fd 48 1b ca 02 	vextractf64x4 ymm2,zmm1,0x2
   e:	62 f3 fd 48 1b cb 02 	vextractf64x4 ymm3,zmm1,0x2
  15:	62 f3 fd 48 1b cc 02 	vextractf64x4 ymm4,zmm1,0x2
  1c:	62 f3 fd 48 1b cd 02 	vextractf64x4 ymm5,zmm1,0x2
  23:	62 f3 fd 48 1b ce 02 	vextractf64x4 ymm6,zmm1,0x2
  2a:	62 f3 fd 48 1b cf 02 	vextractf64x4 ymm7,zmm1,0x2
  31:	62 d3 fd 48 1b c8 02 	vextractf64x4 ymm8,zmm1,0x2
  38:	62 d3 fd 48 1b c9 02 	vextractf64x4 ymm9,zmm1,0x2
  3f:	62 d3 fd 48 1b ca 02 	vextractf64x4 ymm10,zmm1,0x2
  46:	62 d3 fd 48 1b cb 02 	vextractf64x4 ymm11,zmm1,0x2
  4d:	62 d3 fd 48 1b cc 02 	vextractf64x4 ymm12,zmm1,0x2
  54:	62 b3 fd 48 1b c8 02 	vextractf64x4 ymm16,zmm1,0x2
  5b:	62 b3 fd 48 1b c9 02 	vextractf64x4 ymm17,zmm1,0x2
  62:	62 b3 fd 48 1b ca 02 	vextractf64x4 ymm18,zmm1,0x2
  69:	62 b3 fd 48 1b cb 02 	vextractf64x4 ymm19,zmm1,0x2

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]

Show nanoBench command
Results:
- MPERF: 6.91
- 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 unroll_count=500 and no inner loop

Code:

   0:	62 f3 fd 48 1b c0 02 	vextractf64x4 ymm0,zmm0,0x2

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: 0.88
- APERF: 1.0
- UOPS: 1.0
- 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 loop_count=1000 and unroll_count=10

Code:

   0:	62 f3 fd 48 1b c0 02 	vextractf64x4 ymm0,zmm0,0x2

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: 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 f3 fd 48 1b c0 02 	vextractf64x4 ymm0,zmm0,0x2

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: 0.86
- APERF: 1.0
- UOPS: 1.01
- 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

VEXTRACTF64X4 (YMM, ZMM, I8) - 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