VFMADD213PS (YMM, YMM, M256)

With unroll_count=500 and no inner loop

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.58
- APERF: 5.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.19
- APERF: 5.0
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.0
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX

Show nanoBench command
Results:
- MPERF: 4.14
- APERF: 5.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX

Show nanoBench command
Results:
- MPERF: 4.22
- APERF: 5.0
- UOPS: 5.0
- FpuPipeAssignment.Total0: 1.99
- FpuPipeAssignment.Total1: 1.99
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.0
- UOPS: 4.1
- FpuPipeAssignment.Total0: 1.99
- FpuPipeAssignment.Total1: 1.99
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  17:	c4 c2 75 a8 ae 80 00 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+0x80]
  1e:	00 00 
  20:	c4 c2 75 a8 b6 a0 00 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
  27:	00 00 
  29:	c4 c2 75 a8 be c0 00 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
  30:	00 00 
  32:	c4 42 75 a8 86 e0 00 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
  39:	00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 4.32
- APERF: 5.0
- UOPS: 8.0
- FpuPipeAssignment.Total0: 4.0
- FpuPipeAssignment.Total1: 4.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  17:	c4 c2 75 a8 ae 80 00 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+0x80]
  1e:	00 00 
  20:	c4 c2 75 a8 b6 a0 00 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
  27:	00 00 
  29:	c4 c2 75 a8 be c0 00 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
  30:	00 00 
  32:	c4 42 75 a8 86 e0 00 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
  39:	00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 5.05
- APERF: 5.99
- UOPS: 10.0
- FpuPipeAssignment.Total0: 0.03
- FpuPipeAssignment.Total1: 0.03
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  17:	c4 c2 75 a8 ae 80 00 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+0x80]
  1e:	00 00 
  20:	c4 c2 75 a8 b6 a0 00 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
  27:	00 00 
  29:	c4 c2 75 a8 be c0 00 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
  30:	00 00 
  32:	c4 42 75 a8 86 e0 00 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
  39:	00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 4.61
- APERF: 5.45
- UOPS: 8.2
- FpuPipeAssignment.Total0: 3.96
- FpuPipeAssignment.Total1: 3.96
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 12 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  17:	c4 c2 75 a8 ae 80 00 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+0x80]
  1e:	00 00 
  20:	c4 c2 75 a8 b6 a0 00 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
  27:	00 00 
  29:	c4 c2 75 a8 be c0 00 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
  30:	00 00 
  32:	c4 42 75 a8 86 e0 00 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
  39:	00 00 
  3b:	c4 42 75 a8 8e 00 01 	vfmadd213ps ymm9,ymm1,YMMWORD PTR [r14+0x100]
  42:	00 00 
  44:	c4 42 75 a8 96 20 01 	vfmadd213ps ymm10,ymm1,YMMWORD PTR [r14+0x120]
  4b:	00 00 
  4d:	c4 42 75 a8 9e 40 01 	vfmadd213ps ymm11,ymm1,YMMWORD PTR [r14+0x140]
  54:	00 00 
  56:	c4 42 75 a8 a6 60 01 	vfmadd213ps ymm12,ymm1,YMMWORD PTR [r14+0x160]
  5d:	00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
VMOVUPD YMM9, [R14];
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
VMOVUPD YMM10, [R14];
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
VMOVUPD YMM11, [R14];
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
VMOVUPD YMM12, [R14];
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 7.56
- APERF: 9.0
- UOPS: 12.0
- FpuPipeAssignment.Total0: 7.56
- FpuPipeAssignment.Total1: 4.44
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  17:	c4 c2 75 a8 ae 80 00 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+0x80]
  1e:	00 00 
  20:	c4 c2 75 a8 b6 a0 00 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
  27:	00 00 
  29:	c4 c2 75 a8 be c0 00 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
  30:	00 00 
  32:	c4 42 75 a8 86 e0 00 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
  39:	00 00 
  3b:	c4 42 75 a8 8e 00 01 	vfmadd213ps ymm9,ymm1,YMMWORD PTR [r14+0x100]
  42:	00 00 
  44:	c4 42 75 a8 96 20 01 	vfmadd213ps ymm10,ymm1,YMMWORD PTR [r14+0x120]
  4b:	00 00 
  4d:	c4 42 75 a8 9e 40 01 	vfmadd213ps ymm11,ymm1,YMMWORD PTR [r14+0x140]
  54:	00 00 
  56:	c4 42 75 a8 a6 60 01 	vfmadd213ps ymm12,ymm1,YMMWORD PTR [r14+0x160]
  5d:	00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
VMOVUPD YMM9, [R14];
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
VMOVUPD YMM10, [R14];
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
VMOVUPD YMM11, [R14];
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
VMOVUPD YMM12, [R14];
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 8.42
- APERF: 9.99
- UOPS: 14.0
- FpuPipeAssignment.Total0: 6.0
- FpuPipeAssignment.Total1: 6.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 c2 75 a8 06       	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14]
   5:	c4 c2 75 a8 56 20    	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+0x20]
   b:	c4 c2 75 a8 5e 40    	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+0x40]
  11:	c4 c2 75 a8 66 60    	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+0x60]
  17:	c4 c2 75 a8 ae 80 00 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+0x80]
  1e:	00 00 
  20:	c4 c2 75 a8 b6 a0 00 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+0xa0]
  27:	00 00 
  29:	c4 c2 75 a8 be c0 00 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+0xc0]
  30:	00 00 
  32:	c4 42 75 a8 86 e0 00 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+0xe0]
  39:	00 00 
  3b:	c4 42 75 a8 8e 00 01 	vfmadd213ps ymm9,ymm1,YMMWORD PTR [r14+0x100]
  42:	00 00 
  44:	c4 42 75 a8 96 20 01 	vfmadd213ps ymm10,ymm1,YMMWORD PTR [r14+0x120]
  4b:	00 00 
  4d:	c4 42 75 a8 9e 40 01 	vfmadd213ps ymm11,ymm1,YMMWORD PTR [r14+0x140]
  54:	00 00 
  56:	c4 42 75 a8 a6 60 01 	vfmadd213ps ymm12,ymm1,YMMWORD PTR [r14+0x160]
  5d:	00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
VMOVUPD YMM9, [R14];
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
VMOVUPD YMM10, [R14];
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
VMOVUPD YMM11, [R14];
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
VMOVUPD YMM12, [R14];
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 7.66
- APERF: 9.09
- UOPS: 12.2
- FpuPipeAssignment.Total0: 6.0
- FpuPipeAssignment.Total1: 6.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With an indexed addressing mode

With 1 independent instruction

With unroll_count=500 and no inner loop

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.25
- APERF: 5.0
- UOPS: 1.0
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.0
- UOPS: 1.2
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.0
- UOPS: 1.02
- FpuPipeAssignment.Total0: 0.5
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX

Show nanoBench command
Results:
- MPERF: 4.14
- APERF: 5.0
- UOPS: 4.0
- FpuPipeAssignment.Total0: 2.0
- FpuPipeAssignment.Total1: 2.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.01
- UOPS: 5.0
- FpuPipeAssignment.Total0: 1.99
- FpuPipeAssignment.Total1: 1.99
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX

Show nanoBench command
Results:
- MPERF: 4.21
- APERF: 5.01
- UOPS: 4.1
- FpuPipeAssignment.Total0: 1.99
- FpuPipeAssignment.Total1: 1.99
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  1b:	c4 82 75 a8 ac 2e 80 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
  22:	00 00 00 
  25:	c4 82 75 a8 b4 2e a0 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
  2c:	00 00 00 
  2f:	c4 82 75 a8 bc 2e c0 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
  36:	00 00 00 
  39:	c4 02 75 a8 84 2e e0 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
  40:	00 00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 4.5
- APERF: 5.41
- UOPS: 8.0
- FpuPipeAssignment.Total0: 2.72
- FpuPipeAssignment.Total1: 3.01
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  1b:	c4 82 75 a8 ac 2e 80 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
  22:	00 00 00 
  25:	c4 82 75 a8 b4 2e a0 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
  2c:	00 00 00 
  2f:	c4 82 75 a8 bc 2e c0 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
  36:	00 00 00 
  39:	c4 02 75 a8 84 2e e0 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
  40:	00 00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 5.04
- APERF: 5.99
- UOPS: 10.0
- FpuPipeAssignment.Total0: 0.03
- FpuPipeAssignment.Total1: 0.03
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  1b:	c4 82 75 a8 ac 2e 80 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
  22:	00 00 00 
  25:	c4 82 75 a8 b4 2e a0 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
  2c:	00 00 00 
  2f:	c4 82 75 a8 bc 2e c0 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
  36:	00 00 00 
  39:	c4 02 75 a8 84 2e e0 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
  40:	00 00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX

Show nanoBench command
Results:
- MPERF: 4.55
- APERF: 5.4
- UOPS: 8.2
- FpuPipeAssignment.Total0: 1.97
- FpuPipeAssignment.Total1: 1.97
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With 12 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  1b:	c4 82 75 a8 ac 2e 80 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
  22:	00 00 00 
  25:	c4 82 75 a8 b4 2e a0 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
  2c:	00 00 00 
  2f:	c4 82 75 a8 bc 2e c0 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
  36:	00 00 00 
  39:	c4 02 75 a8 84 2e e0 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
  40:	00 00 00 
  43:	c4 02 75 a8 8c 2e 00 	vfmadd213ps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100]
  4a:	01 00 00 
  4d:	c4 02 75 a8 94 2e 20 	vfmadd213ps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120]
  54:	01 00 00 
  57:	c4 02 75 a8 9c 2e 40 	vfmadd213ps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140]
  5e:	01 00 00 
  61:	c4 02 75 a8 a4 2e 60 	vfmadd213ps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160]
  68:	01 00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
VMOVUPD YMM9, [R14];
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
VMOVUPD YMM10, [R14];
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
VMOVUPD YMM11, [R14];
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
VMOVUPD YMM12, [R14];
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 7.8
- APERF: 9.25
- UOPS: 12.0
- FpuPipeAssignment.Total0: 6.02
- FpuPipeAssignment.Total1: 5.98
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  1b:	c4 82 75 a8 ac 2e 80 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
  22:	00 00 00 
  25:	c4 82 75 a8 b4 2e a0 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
  2c:	00 00 00 
  2f:	c4 82 75 a8 bc 2e c0 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
  36:	00 00 00 
  39:	c4 02 75 a8 84 2e e0 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
  40:	00 00 00 
  43:	c4 02 75 a8 8c 2e 00 	vfmadd213ps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100]
  4a:	01 00 00 
  4d:	c4 02 75 a8 94 2e 20 	vfmadd213ps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120]
  54:	01 00 00 
  57:	c4 02 75 a8 9c 2e 40 	vfmadd213ps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140]
  5e:	01 00 00 
  61:	c4 02 75 a8 a4 2e 60 	vfmadd213ps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160]
  68:	01 00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
VMOVUPD YMM9, [R14];
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
VMOVUPD YMM10, [R14];
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
VMOVUPD YMM11, [R14];
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
VMOVUPD YMM12, [R14];
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 8.42
- APERF: 9.99
- UOPS: 14.0
- FpuPipeAssignment.Total0: 6.0
- FpuPipeAssignment.Total1: 6.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	c4 82 75 a8 04 2e    	vfmadd213ps ymm0,ymm1,YMMWORD PTR [r14+r13*1]
   6:	c4 82 75 a8 54 2e 20 	vfmadd213ps ymm2,ymm1,YMMWORD PTR [r14+r13*1+0x20]
   d:	c4 82 75 a8 5c 2e 40 	vfmadd213ps ymm3,ymm1,YMMWORD PTR [r14+r13*1+0x40]
  14:	c4 82 75 a8 64 2e 60 	vfmadd213ps ymm4,ymm1,YMMWORD PTR [r14+r13*1+0x60]
  1b:	c4 82 75 a8 ac 2e 80 	vfmadd213ps ymm5,ymm1,YMMWORD PTR [r14+r13*1+0x80]
  22:	00 00 00 
  25:	c4 82 75 a8 b4 2e a0 	vfmadd213ps ymm6,ymm1,YMMWORD PTR [r14+r13*1+0xa0]
  2c:	00 00 00 
  2f:	c4 82 75 a8 bc 2e c0 	vfmadd213ps ymm7,ymm1,YMMWORD PTR [r14+r13*1+0xc0]
  36:	00 00 00 
  39:	c4 02 75 a8 84 2e e0 	vfmadd213ps ymm8,ymm1,YMMWORD PTR [r14+r13*1+0xe0]
  40:	00 00 00 
  43:	c4 02 75 a8 8c 2e 00 	vfmadd213ps ymm9,ymm1,YMMWORD PTR [r14+r13*1+0x100]
  4a:	01 00 00 
  4d:	c4 02 75 a8 94 2e 20 	vfmadd213ps ymm10,ymm1,YMMWORD PTR [r14+r13*1+0x120]
  54:	01 00 00 
  57:	c4 02 75 a8 9c 2e 40 	vfmadd213ps ymm11,ymm1,YMMWORD PTR [r14+r13*1+0x140]
  5e:	01 00 00 
  61:	c4 02 75 a8 a4 2e 60 	vfmadd213ps ymm12,ymm1,YMMWORD PTR [r14+r13*1+0x160]
  68:	01 00 00

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOV [R14+16], RAX;
MOV [R14+24], RAX;
VMOVUPD YMM0, [R14];
VMOVUPD YMM1, [R14];
XOR R13, R13;
VMOVUPD YMM2, [R14];
MOV [R14+32], RAX;
MOV [R14+40], RAX;
MOV [R14+48], RAX;
MOV [R14+56], RAX;
VMOVUPD YMM3, [R14];
MOV [R14+64], RAX;
MOV [R14+72], RAX;
MOV [R14+80], RAX;
MOV [R14+88], RAX;
VMOVUPD YMM4, [R14];
MOV [R14+96], RAX;
MOV [R14+104], RAX;
MOV [R14+112], RAX;
MOV [R14+120], RAX;
VMOVUPD YMM5, [R14];
MOV [R14+128], RAX;
MOV [R14+136], RAX;
MOV [R14+144], RAX;
MOV [R14+152], RAX;
VMOVUPD YMM6, [R14];
MOV [R14+160], RAX;
MOV [R14+168], RAX;
MOV [R14+176], RAX;
MOV [R14+184], RAX;
VMOVUPD YMM7, [R14];
MOV [R14+192], RAX;
MOV [R14+200], RAX;
MOV [R14+208], RAX;
MOV [R14+216], RAX;
VMOVUPD YMM8, [R14];
MOV [R14+224], RAX;
MOV [R14+232], RAX;
MOV [R14+240], RAX;
MOV [R14+248], RAX;
VMOVUPD YMM9, [R14];
MOV [R14+256], RAX;
MOV [R14+264], RAX;
MOV [R14+272], RAX;
MOV [R14+280], RAX;
VMOVUPD YMM10, [R14];
MOV [R14+288], RAX;
MOV [R14+296], RAX;
MOV [R14+304], RAX;
MOV [R14+312], RAX;
VMOVUPD YMM11, [R14];
MOV [R14+320], RAX;
MOV [R14+328], RAX;
MOV [R14+336], RAX;
MOV [R14+344], RAX;
VMOVUPD YMM12, [R14];
MOV [R14+352], RAX;
MOV [R14+360], RAX;
MOV [R14+368], RAX;
MOV [R14+376], RAX

Show nanoBench command
Results:
- MPERF: 7.91
- APERF: 9.39
- UOPS: 12.2
- FpuPipeAssignment.Total0: 6.0
- FpuPipeAssignment.Total1: 6.0
- FpuPipeAssignment.Total2: 0.0
- FpuPipeAssignment.Total3: 0.0
- DIV_CYCLES: 0.0

VFMADD213PS (YMM, YMM, M256) - 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 12 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 12 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