VMOVAPS (ZMM, M512)

With unroll_count=200 and no inner loop

Code:

   0:	62 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 3.49
- APERF: 4.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	62 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 3.44
- APERF: 4.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	62 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- 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 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]
  1b:	62 d1 7c 48 28 66 04 	vmovaps zmm4,ZMMWORD PTR [r14+0x100]
  22:	62 d1 7c 48 28 6e 05 	vmovaps zmm5,ZMMWORD PTR [r14+0x140]
  29:	62 d1 7c 48 28 76 06 	vmovaps zmm6,ZMMWORD PTR [r14+0x180]
  30:	62 d1 7c 48 28 7e 07 	vmovaps zmm7,ZMMWORD PTR [r14+0x1c0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX

Show nanoBench command
Results:
- MPERF: 7.05
- APERF: 8.28
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]
  1b:	62 d1 7c 48 28 66 04 	vmovaps zmm4,ZMMWORD PTR [r14+0x100]
  22:	62 d1 7c 48 28 6e 05 	vmovaps zmm5,ZMMWORD PTR [r14+0x140]
  29:	62 d1 7c 48 28 76 06 	vmovaps zmm6,ZMMWORD PTR [r14+0x180]
  30:	62 d1 7c 48 28 7e 07 	vmovaps zmm7,ZMMWORD PTR [r14+0x1c0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX

Show nanoBench command
Results:
- MPERF: 6.96
- APERF: 8.06
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]
  1b:	62 d1 7c 48 28 66 04 	vmovaps zmm4,ZMMWORD PTR [r14+0x100]
  22:	62 d1 7c 48 28 6e 05 	vmovaps zmm5,ZMMWORD PTR [r14+0x140]
  29:	62 d1 7c 48 28 76 06 	vmovaps zmm6,ZMMWORD PTR [r14+0x180]
  30:	62 d1 7c 48 28 7e 07 	vmovaps zmm7,ZMMWORD PTR [r14+0x1c0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX

Show nanoBench command
Results:
- MPERF: 7.01
- APERF: 8.14
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- 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 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]
  1b:	62 d1 7c 48 28 66 04 	vmovaps zmm4,ZMMWORD PTR [r14+0x100]
  22:	62 d1 7c 48 28 6e 05 	vmovaps zmm5,ZMMWORD PTR [r14+0x140]
  29:	62 d1 7c 48 28 76 06 	vmovaps zmm6,ZMMWORD PTR [r14+0x180]
  30:	62 d1 7c 48 28 7e 07 	vmovaps zmm7,ZMMWORD PTR [r14+0x1c0]
  37:	62 51 7c 48 28 46 08 	vmovaps zmm8,ZMMWORD PTR [r14+0x200]
  3e:	62 51 7c 48 28 4e 09 	vmovaps zmm9,ZMMWORD PTR [r14+0x240]
  45:	62 51 7c 48 28 56 0a 	vmovaps zmm10,ZMMWORD PTR [r14+0x280]
  4c:	62 51 7c 48 28 5e 0b 	vmovaps zmm11,ZMMWORD PTR [r14+0x2c0]
  53:	62 51 7c 48 28 66 0c 	vmovaps zmm12,ZMMWORD PTR [r14+0x300]
  5a:	62 c1 7c 48 28 46 0d 	vmovaps zmm16,ZMMWORD PTR [r14+0x340]
  61:	62 c1 7c 48 28 4e 0e 	vmovaps zmm17,ZMMWORD PTR [r14+0x380]
  68:	62 c1 7c 48 28 56 0f 	vmovaps zmm18,ZMMWORD PTR [r14+0x3c0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX;
MOV [R14+512], RAX;
MOV [R14+520], RAX;
MOV [R14+528], RAX;
MOV [R14+536], RAX;
MOV [R14+544], RAX;
MOV [R14+552], RAX;
MOV [R14+560], RAX;
MOV [R14+568], RAX;
MOV [R14+576], RAX;
MOV [R14+584], RAX;
MOV [R14+592], RAX;
MOV [R14+600], RAX;
MOV [R14+608], RAX;
MOV [R14+616], RAX;
MOV [R14+624], RAX;
MOV [R14+632], RAX;
MOV [R14+640], RAX;
MOV [R14+648], RAX;
MOV [R14+656], RAX;
MOV [R14+664], RAX;
MOV [R14+672], RAX;
MOV [R14+680], RAX;
MOV [R14+688], RAX;
MOV [R14+696], RAX;
MOV [R14+704], RAX;
MOV [R14+712], RAX;
MOV [R14+720], RAX;
MOV [R14+728], RAX;
MOV [R14+736], RAX;
MOV [R14+744], RAX;
MOV [R14+752], RAX;
MOV [R14+760], RAX;
MOV [R14+768], RAX;
MOV [R14+776], RAX;
MOV [R14+784], RAX;
MOV [R14+792], RAX;
MOV [R14+800], RAX;
MOV [R14+808], RAX;
MOV [R14+816], RAX;
MOV [R14+824], RAX;
MOV [R14+832], RAX;
MOV [R14+840], RAX;
MOV [R14+848], RAX;
MOV [R14+856], RAX;
MOV [R14+864], RAX;
MOV [R14+872], RAX;
MOV [R14+880], RAX;
MOV [R14+888], RAX;
MOV [R14+896], RAX;
MOV [R14+904], RAX;
MOV [R14+912], RAX;
MOV [R14+920], RAX;
MOV [R14+928], RAX;
MOV [R14+936], RAX;
MOV [R14+944], RAX;
MOV [R14+952], RAX;
MOV [R14+960], RAX;
MOV [R14+968], RAX;
MOV [R14+976], RAX;
MOV [R14+984], RAX;
MOV [R14+992], RAX;
MOV [R14+1000], RAX;
MOV [R14+1008], RAX;
MOV [R14+1016], RAX

Show nanoBench command
Results:
- MPERF: 14.1
- APERF: 16.42
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]
  1b:	62 d1 7c 48 28 66 04 	vmovaps zmm4,ZMMWORD PTR [r14+0x100]
  22:	62 d1 7c 48 28 6e 05 	vmovaps zmm5,ZMMWORD PTR [r14+0x140]
  29:	62 d1 7c 48 28 76 06 	vmovaps zmm6,ZMMWORD PTR [r14+0x180]
  30:	62 d1 7c 48 28 7e 07 	vmovaps zmm7,ZMMWORD PTR [r14+0x1c0]
  37:	62 51 7c 48 28 46 08 	vmovaps zmm8,ZMMWORD PTR [r14+0x200]
  3e:	62 51 7c 48 28 4e 09 	vmovaps zmm9,ZMMWORD PTR [r14+0x240]
  45:	62 51 7c 48 28 56 0a 	vmovaps zmm10,ZMMWORD PTR [r14+0x280]
  4c:	62 51 7c 48 28 5e 0b 	vmovaps zmm11,ZMMWORD PTR [r14+0x2c0]
  53:	62 51 7c 48 28 66 0c 	vmovaps zmm12,ZMMWORD PTR [r14+0x300]
  5a:	62 c1 7c 48 28 46 0d 	vmovaps zmm16,ZMMWORD PTR [r14+0x340]
  61:	62 c1 7c 48 28 4e 0e 	vmovaps zmm17,ZMMWORD PTR [r14+0x380]
  68:	62 c1 7c 48 28 56 0f 	vmovaps zmm18,ZMMWORD PTR [r14+0x3c0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX;
MOV [R14+512], RAX;
MOV [R14+520], RAX;
MOV [R14+528], RAX;
MOV [R14+536], RAX;
MOV [R14+544], RAX;
MOV [R14+552], RAX;
MOV [R14+560], RAX;
MOV [R14+568], RAX;
MOV [R14+576], RAX;
MOV [R14+584], RAX;
MOV [R14+592], RAX;
MOV [R14+600], RAX;
MOV [R14+608], RAX;
MOV [R14+616], RAX;
MOV [R14+624], RAX;
MOV [R14+632], RAX;
MOV [R14+640], RAX;
MOV [R14+648], RAX;
MOV [R14+656], RAX;
MOV [R14+664], RAX;
MOV [R14+672], RAX;
MOV [R14+680], RAX;
MOV [R14+688], RAX;
MOV [R14+696], RAX;
MOV [R14+704], RAX;
MOV [R14+712], RAX;
MOV [R14+720], RAX;
MOV [R14+728], RAX;
MOV [R14+736], RAX;
MOV [R14+744], RAX;
MOV [R14+752], RAX;
MOV [R14+760], RAX;
MOV [R14+768], RAX;
MOV [R14+776], RAX;
MOV [R14+784], RAX;
MOV [R14+792], RAX;
MOV [R14+800], RAX;
MOV [R14+808], RAX;
MOV [R14+816], RAX;
MOV [R14+824], RAX;
MOV [R14+832], RAX;
MOV [R14+840], RAX;
MOV [R14+848], RAX;
MOV [R14+856], RAX;
MOV [R14+864], RAX;
MOV [R14+872], RAX;
MOV [R14+880], RAX;
MOV [R14+888], RAX;
MOV [R14+896], RAX;
MOV [R14+904], RAX;
MOV [R14+912], RAX;
MOV [R14+920], RAX;
MOV [R14+928], RAX;
MOV [R14+936], RAX;
MOV [R14+944], RAX;
MOV [R14+952], RAX;
MOV [R14+960], RAX;
MOV [R14+968], RAX;
MOV [R14+976], RAX;
MOV [R14+984], RAX;
MOV [R14+992], RAX;
MOV [R14+1000], RAX;
MOV [R14+1008], RAX;
MOV [R14+1016], RAX

Show nanoBench command
Results:
- MPERF: 13.82
- APERF: 16.01
- UOPS: 17.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 d1 7c 48 28 06    	vmovaps zmm0,ZMMWORD PTR [r14]
   6:	62 d1 7c 48 28 4e 01 	vmovaps zmm1,ZMMWORD PTR [r14+0x40]
   d:	62 d1 7c 48 28 56 02 	vmovaps zmm2,ZMMWORD PTR [r14+0x80]
  14:	62 d1 7c 48 28 5e 03 	vmovaps zmm3,ZMMWORD PTR [r14+0xc0]
  1b:	62 d1 7c 48 28 66 04 	vmovaps zmm4,ZMMWORD PTR [r14+0x100]
  22:	62 d1 7c 48 28 6e 05 	vmovaps zmm5,ZMMWORD PTR [r14+0x140]
  29:	62 d1 7c 48 28 76 06 	vmovaps zmm6,ZMMWORD PTR [r14+0x180]
  30:	62 d1 7c 48 28 7e 07 	vmovaps zmm7,ZMMWORD PTR [r14+0x1c0]
  37:	62 51 7c 48 28 46 08 	vmovaps zmm8,ZMMWORD PTR [r14+0x200]
  3e:	62 51 7c 48 28 4e 09 	vmovaps zmm9,ZMMWORD PTR [r14+0x240]
  45:	62 51 7c 48 28 56 0a 	vmovaps zmm10,ZMMWORD PTR [r14+0x280]
  4c:	62 51 7c 48 28 5e 0b 	vmovaps zmm11,ZMMWORD PTR [r14+0x2c0]
  53:	62 51 7c 48 28 66 0c 	vmovaps zmm12,ZMMWORD PTR [r14+0x300]
  5a:	62 c1 7c 48 28 46 0d 	vmovaps zmm16,ZMMWORD PTR [r14+0x340]
  61:	62 c1 7c 48 28 4e 0e 	vmovaps zmm17,ZMMWORD PTR [r14+0x380]
  68:	62 c1 7c 48 28 56 0f 	vmovaps zmm18,ZMMWORD PTR [r14+0x3c0]

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;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX;
MOV [R14+512], RAX;
MOV [R14+520], RAX;
MOV [R14+528], RAX;
MOV [R14+536], RAX;
MOV [R14+544], RAX;
MOV [R14+552], RAX;
MOV [R14+560], RAX;
MOV [R14+568], RAX;
MOV [R14+576], RAX;
MOV [R14+584], RAX;
MOV [R14+592], RAX;
MOV [R14+600], RAX;
MOV [R14+608], RAX;
MOV [R14+616], RAX;
MOV [R14+624], RAX;
MOV [R14+632], RAX;
MOV [R14+640], RAX;
MOV [R14+648], RAX;
MOV [R14+656], RAX;
MOV [R14+664], RAX;
MOV [R14+672], RAX;
MOV [R14+680], RAX;
MOV [R14+688], RAX;
MOV [R14+696], RAX;
MOV [R14+704], RAX;
MOV [R14+712], RAX;
MOV [R14+720], RAX;
MOV [R14+728], RAX;
MOV [R14+736], RAX;
MOV [R14+744], RAX;
MOV [R14+752], RAX;
MOV [R14+760], RAX;
MOV [R14+768], RAX;
MOV [R14+776], RAX;
MOV [R14+784], RAX;
MOV [R14+792], RAX;
MOV [R14+800], RAX;
MOV [R14+808], RAX;
MOV [R14+816], RAX;
MOV [R14+824], RAX;
MOV [R14+832], RAX;
MOV [R14+840], RAX;
MOV [R14+848], RAX;
MOV [R14+856], RAX;
MOV [R14+864], RAX;
MOV [R14+872], RAX;
MOV [R14+880], RAX;
MOV [R14+888], RAX;
MOV [R14+896], RAX;
MOV [R14+904], RAX;
MOV [R14+912], RAX;
MOV [R14+920], RAX;
MOV [R14+928], RAX;
MOV [R14+936], RAX;
MOV [R14+944], RAX;
MOV [R14+952], RAX;
MOV [R14+960], RAX;
MOV [R14+968], RAX;
MOV [R14+976], RAX;
MOV [R14+984], RAX;
MOV [R14+992], RAX;
MOV [R14+1000], RAX;
MOV [R14+1008], RAX;
MOV [R14+1016], RAX

Show nanoBench command
Results:
- MPERF: 14.71
- APERF: 17.05
- UOPS: 16.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With an indexed addressing mode

With 1 independent instruction

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	62 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 4.23
- APERF: 4.92
- UOPS: 4.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	62 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	62 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 3.45
- APERF: 4.0
- UOPS: 4.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- 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 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03 
  1f:	62 91 7c 48 28 64 2e 	vmovaps zmm4,ZMMWORD PTR [r14+r13*1+0x100]
  26:	04 
  27:	62 91 7c 48 28 6c 2e 	vmovaps zmm5,ZMMWORD PTR [r14+r13*1+0x140]
  2e:	05 
  2f:	62 91 7c 48 28 74 2e 	vmovaps zmm6,ZMMWORD PTR [r14+r13*1+0x180]
  36:	06 
  37:	62 91 7c 48 28 7c 2e 	vmovaps zmm7,ZMMWORD PTR [r14+r13*1+0x1c0]
  3e:	07

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX

Show nanoBench command
Results:
- MPERF: 9.56
- APERF: 11.21
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03 
  1f:	62 91 7c 48 28 64 2e 	vmovaps zmm4,ZMMWORD PTR [r14+r13*1+0x100]
  26:	04 
  27:	62 91 7c 48 28 6c 2e 	vmovaps zmm5,ZMMWORD PTR [r14+r13*1+0x140]
  2e:	05 
  2f:	62 91 7c 48 28 74 2e 	vmovaps zmm6,ZMMWORD PTR [r14+r13*1+0x180]
  36:	06 
  37:	62 91 7c 48 28 7c 2e 	vmovaps zmm7,ZMMWORD PTR [r14+r13*1+0x1c0]
  3e:	07

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX

Show nanoBench command
Results:
- MPERF: 8.41
- APERF: 9.74
- UOPS: 9.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03 
  1f:	62 91 7c 48 28 64 2e 	vmovaps zmm4,ZMMWORD PTR [r14+r13*1+0x100]
  26:	04 
  27:	62 91 7c 48 28 6c 2e 	vmovaps zmm5,ZMMWORD PTR [r14+r13*1+0x140]
  2e:	05 
  2f:	62 91 7c 48 28 74 2e 	vmovaps zmm6,ZMMWORD PTR [r14+r13*1+0x180]
  36:	06 
  37:	62 91 7c 48 28 7c 2e 	vmovaps zmm7,ZMMWORD PTR [r14+r13*1+0x1c0]
  3e:	07

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX

Show nanoBench command
Results:
- MPERF: 8.32
- APERF: 9.64
- UOPS: 8.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- 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 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03 
  1f:	62 91 7c 48 28 64 2e 	vmovaps zmm4,ZMMWORD PTR [r14+r13*1+0x100]
  26:	04 
  27:	62 91 7c 48 28 6c 2e 	vmovaps zmm5,ZMMWORD PTR [r14+r13*1+0x140]
  2e:	05 
  2f:	62 91 7c 48 28 74 2e 	vmovaps zmm6,ZMMWORD PTR [r14+r13*1+0x180]
  36:	06 
  37:	62 91 7c 48 28 7c 2e 	vmovaps zmm7,ZMMWORD PTR [r14+r13*1+0x1c0]
  3e:	07 
  3f:	62 11 7c 48 28 44 2e 	vmovaps zmm8,ZMMWORD PTR [r14+r13*1+0x200]
  46:	08 
  47:	62 11 7c 48 28 4c 2e 	vmovaps zmm9,ZMMWORD PTR [r14+r13*1+0x240]
  4e:	09 
  4f:	62 11 7c 48 28 54 2e 	vmovaps zmm10,ZMMWORD PTR [r14+r13*1+0x280]
  56:	0a 
  57:	62 11 7c 48 28 5c 2e 	vmovaps zmm11,ZMMWORD PTR [r14+r13*1+0x2c0]
  5e:	0b 
  5f:	62 11 7c 48 28 64 2e 	vmovaps zmm12,ZMMWORD PTR [r14+r13*1+0x300]
  66:	0c 
  67:	62 81 7c 48 28 44 2e 	vmovaps zmm16,ZMMWORD PTR [r14+r13*1+0x340]
  6e:	0d 
  6f:	62 81 7c 48 28 4c 2e 	vmovaps zmm17,ZMMWORD PTR [r14+r13*1+0x380]
  76:	0e 
  77:	62 81 7c 48 28 54 2e 	vmovaps zmm18,ZMMWORD PTR [r14+r13*1+0x3c0]
  7e:	0f

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX;
MOV [R14+512], RAX;
MOV [R14+520], RAX;
MOV [R14+528], RAX;
MOV [R14+536], RAX;
MOV [R14+544], RAX;
MOV [R14+552], RAX;
MOV [R14+560], RAX;
MOV [R14+568], RAX;
MOV [R14+576], RAX;
MOV [R14+584], RAX;
MOV [R14+592], RAX;
MOV [R14+600], RAX;
MOV [R14+608], RAX;
MOV [R14+616], RAX;
MOV [R14+624], RAX;
MOV [R14+632], RAX;
MOV [R14+640], RAX;
MOV [R14+648], RAX;
MOV [R14+656], RAX;
MOV [R14+664], RAX;
MOV [R14+672], RAX;
MOV [R14+680], RAX;
MOV [R14+688], RAX;
MOV [R14+696], RAX;
MOV [R14+704], RAX;
MOV [R14+712], RAX;
MOV [R14+720], RAX;
MOV [R14+728], RAX;
MOV [R14+736], RAX;
MOV [R14+744], RAX;
MOV [R14+752], RAX;
MOV [R14+760], RAX;
MOV [R14+768], RAX;
MOV [R14+776], RAX;
MOV [R14+784], RAX;
MOV [R14+792], RAX;
MOV [R14+800], RAX;
MOV [R14+808], RAX;
MOV [R14+816], RAX;
MOV [R14+824], RAX;
MOV [R14+832], RAX;
MOV [R14+840], RAX;
MOV [R14+848], RAX;
MOV [R14+856], RAX;
MOV [R14+864], RAX;
MOV [R14+872], RAX;
MOV [R14+880], RAX;
MOV [R14+888], RAX;
MOV [R14+896], RAX;
MOV [R14+904], RAX;
MOV [R14+912], RAX;
MOV [R14+920], RAX;
MOV [R14+928], RAX;
MOV [R14+936], RAX;
MOV [R14+944], RAX;
MOV [R14+952], RAX;
MOV [R14+960], RAX;
MOV [R14+968], RAX;
MOV [R14+976], RAX;
MOV [R14+984], RAX;
MOV [R14+992], RAX;
MOV [R14+1000], RAX;
MOV [R14+1008], RAX;
MOV [R14+1016], RAX

Show nanoBench command
Results:
- MPERF: 16.22
- APERF: 18.84
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03 
  1f:	62 91 7c 48 28 64 2e 	vmovaps zmm4,ZMMWORD PTR [r14+r13*1+0x100]
  26:	04 
  27:	62 91 7c 48 28 6c 2e 	vmovaps zmm5,ZMMWORD PTR [r14+r13*1+0x140]
  2e:	05 
  2f:	62 91 7c 48 28 74 2e 	vmovaps zmm6,ZMMWORD PTR [r14+r13*1+0x180]
  36:	06 
  37:	62 91 7c 48 28 7c 2e 	vmovaps zmm7,ZMMWORD PTR [r14+r13*1+0x1c0]
  3e:	07 
  3f:	62 11 7c 48 28 44 2e 	vmovaps zmm8,ZMMWORD PTR [r14+r13*1+0x200]
  46:	08 
  47:	62 11 7c 48 28 4c 2e 	vmovaps zmm9,ZMMWORD PTR [r14+r13*1+0x240]
  4e:	09 
  4f:	62 11 7c 48 28 54 2e 	vmovaps zmm10,ZMMWORD PTR [r14+r13*1+0x280]
  56:	0a 
  57:	62 11 7c 48 28 5c 2e 	vmovaps zmm11,ZMMWORD PTR [r14+r13*1+0x2c0]
  5e:	0b 
  5f:	62 11 7c 48 28 64 2e 	vmovaps zmm12,ZMMWORD PTR [r14+r13*1+0x300]
  66:	0c 
  67:	62 81 7c 48 28 44 2e 	vmovaps zmm16,ZMMWORD PTR [r14+r13*1+0x340]
  6e:	0d 
  6f:	62 81 7c 48 28 4c 2e 	vmovaps zmm17,ZMMWORD PTR [r14+r13*1+0x380]
  76:	0e 
  77:	62 81 7c 48 28 54 2e 	vmovaps zmm18,ZMMWORD PTR [r14+r13*1+0x3c0]
  7e:	0f

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX;
MOV [R14+512], RAX;
MOV [R14+520], RAX;
MOV [R14+528], RAX;
MOV [R14+536], RAX;
MOV [R14+544], RAX;
MOV [R14+552], RAX;
MOV [R14+560], RAX;
MOV [R14+568], RAX;
MOV [R14+576], RAX;
MOV [R14+584], RAX;
MOV [R14+592], RAX;
MOV [R14+600], RAX;
MOV [R14+608], RAX;
MOV [R14+616], RAX;
MOV [R14+624], RAX;
MOV [R14+632], RAX;
MOV [R14+640], RAX;
MOV [R14+648], RAX;
MOV [R14+656], RAX;
MOV [R14+664], RAX;
MOV [R14+672], RAX;
MOV [R14+680], RAX;
MOV [R14+688], RAX;
MOV [R14+696], RAX;
MOV [R14+704], RAX;
MOV [R14+712], RAX;
MOV [R14+720], RAX;
MOV [R14+728], RAX;
MOV [R14+736], RAX;
MOV [R14+744], RAX;
MOV [R14+752], RAX;
MOV [R14+760], RAX;
MOV [R14+768], RAX;
MOV [R14+776], RAX;
MOV [R14+784], RAX;
MOV [R14+792], RAX;
MOV [R14+800], RAX;
MOV [R14+808], RAX;
MOV [R14+816], RAX;
MOV [R14+824], RAX;
MOV [R14+832], RAX;
MOV [R14+840], RAX;
MOV [R14+848], RAX;
MOV [R14+856], RAX;
MOV [R14+864], RAX;
MOV [R14+872], RAX;
MOV [R14+880], RAX;
MOV [R14+888], RAX;
MOV [R14+896], RAX;
MOV [R14+904], RAX;
MOV [R14+912], RAX;
MOV [R14+920], RAX;
MOV [R14+928], RAX;
MOV [R14+936], RAX;
MOV [R14+944], RAX;
MOV [R14+952], RAX;
MOV [R14+960], RAX;
MOV [R14+968], RAX;
MOV [R14+976], RAX;
MOV [R14+984], RAX;
MOV [R14+992], RAX;
MOV [R14+1000], RAX;
MOV [R14+1008], RAX;
MOV [R14+1016], RAX

Show nanoBench command
Results:
- MPERF: 14.8
- APERF: 17.15
- UOPS: 17.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 91 7c 48 28 04 2e 	vmovaps zmm0,ZMMWORD PTR [r14+r13*1]
   7:	62 91 7c 48 28 4c 2e 	vmovaps zmm1,ZMMWORD PTR [r14+r13*1+0x40]
   e:	01 
   f:	62 91 7c 48 28 54 2e 	vmovaps zmm2,ZMMWORD PTR [r14+r13*1+0x80]
  16:	02 
  17:	62 91 7c 48 28 5c 2e 	vmovaps zmm3,ZMMWORD PTR [r14+r13*1+0xc0]
  1e:	03 
  1f:	62 91 7c 48 28 64 2e 	vmovaps zmm4,ZMMWORD PTR [r14+r13*1+0x100]
  26:	04 
  27:	62 91 7c 48 28 6c 2e 	vmovaps zmm5,ZMMWORD PTR [r14+r13*1+0x140]
  2e:	05 
  2f:	62 91 7c 48 28 74 2e 	vmovaps zmm6,ZMMWORD PTR [r14+r13*1+0x180]
  36:	06 
  37:	62 91 7c 48 28 7c 2e 	vmovaps zmm7,ZMMWORD PTR [r14+r13*1+0x1c0]
  3e:	07 
  3f:	62 11 7c 48 28 44 2e 	vmovaps zmm8,ZMMWORD PTR [r14+r13*1+0x200]
  46:	08 
  47:	62 11 7c 48 28 4c 2e 	vmovaps zmm9,ZMMWORD PTR [r14+r13*1+0x240]
  4e:	09 
  4f:	62 11 7c 48 28 54 2e 	vmovaps zmm10,ZMMWORD PTR [r14+r13*1+0x280]
  56:	0a 
  57:	62 11 7c 48 28 5c 2e 	vmovaps zmm11,ZMMWORD PTR [r14+r13*1+0x2c0]
  5e:	0b 
  5f:	62 11 7c 48 28 64 2e 	vmovaps zmm12,ZMMWORD PTR [r14+r13*1+0x300]
  66:	0c 
  67:	62 81 7c 48 28 44 2e 	vmovaps zmm16,ZMMWORD PTR [r14+r13*1+0x340]
  6e:	0d 
  6f:	62 81 7c 48 28 4c 2e 	vmovaps zmm17,ZMMWORD PTR [r14+r13*1+0x380]
  76:	0e 
  77:	62 81 7c 48 28 54 2e 	vmovaps zmm18,ZMMWORD PTR [r14+r13*1+0x3c0]
  7e:	0f

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;
XOR R13, R13;
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX;
MOV [R14+384], RAX;
MOV [R14+392], RAX;
MOV [R14+400], RAX;
MOV [R14+408], RAX;
MOV [R14+416], RAX;
MOV [R14+424], RAX;
MOV [R14+432], RAX;
MOV [R14+440], RAX;
MOV [R14+448], RAX;
MOV [R14+456], RAX;
MOV [R14+464], RAX;
MOV [R14+472], RAX;
MOV [R14+480], RAX;
MOV [R14+488], RAX;
MOV [R14+496], RAX;
MOV [R14+504], RAX;
MOV [R14+512], RAX;
MOV [R14+520], RAX;
MOV [R14+528], RAX;
MOV [R14+536], RAX;
MOV [R14+544], RAX;
MOV [R14+552], RAX;
MOV [R14+560], RAX;
MOV [R14+568], RAX;
MOV [R14+576], RAX;
MOV [R14+584], RAX;
MOV [R14+592], RAX;
MOV [R14+600], RAX;
MOV [R14+608], RAX;
MOV [R14+616], RAX;
MOV [R14+624], RAX;
MOV [R14+632], RAX;
MOV [R14+640], RAX;
MOV [R14+648], RAX;
MOV [R14+656], RAX;
MOV [R14+664], RAX;
MOV [R14+672], RAX;
MOV [R14+680], RAX;
MOV [R14+688], RAX;
MOV [R14+696], RAX;
MOV [R14+704], RAX;
MOV [R14+712], RAX;
MOV [R14+720], RAX;
MOV [R14+728], RAX;
MOV [R14+736], RAX;
MOV [R14+744], RAX;
MOV [R14+752], RAX;
MOV [R14+760], RAX;
MOV [R14+768], RAX;
MOV [R14+776], RAX;
MOV [R14+784], RAX;
MOV [R14+792], RAX;
MOV [R14+800], RAX;
MOV [R14+808], RAX;
MOV [R14+816], RAX;
MOV [R14+824], RAX;
MOV [R14+832], RAX;
MOV [R14+840], RAX;
MOV [R14+848], RAX;
MOV [R14+856], RAX;
MOV [R14+864], RAX;
MOV [R14+872], RAX;
MOV [R14+880], RAX;
MOV [R14+888], RAX;
MOV [R14+896], RAX;
MOV [R14+904], RAX;
MOV [R14+912], RAX;
MOV [R14+920], RAX;
MOV [R14+928], RAX;
MOV [R14+936], RAX;
MOV [R14+944], RAX;
MOV [R14+952], RAX;
MOV [R14+960], RAX;
MOV [R14+968], RAX;
MOV [R14+976], RAX;
MOV [R14+984], RAX;
MOV [R14+992], RAX;
MOV [R14+1000], RAX;
MOV [R14+1008], RAX;
MOV [R14+1016], RAX

Show nanoBench command
Results:
- MPERF: 16.32
- APERF: 18.93
- UOPS: 16.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VMOVAPS (ZMM, M512) - 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