VCVTPS2PD (ZMM, YMM)

With unroll_count=500 and no inner loop

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 1.21
- APERF: 1.34
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.67
- FpuPipeAssignment.Total2: 0.67
- FpuPipeAssignment.Total3: 0.67
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 1.15
- APERF: 1.34
- UOPS: 2.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.67
- FpuPipeAssignment.Total2: 0.67
- FpuPipeAssignment.Total3: 0.67
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 1.15
- APERF: 1.34
- UOPS: 2.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.67
- FpuPipeAssignment.Total2: 0.67
- FpuPipeAssignment.Total3: 0.67
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 4 independent instructions

With unroll_count=200 and no inner loop

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.7
- APERF: 5.32
- UOPS: 8.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.67
- FpuPipeAssignment.Total2: 2.66
- FpuPipeAssignment.Total3: 2.67
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=2

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.61
- APERF: 5.35
- UOPS: 8.5
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.66
- FpuPipeAssignment.Total2: 2.67
- FpuPipeAssignment.Total3: 2.67
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=20

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 4.61
- APERF: 5.35
- UOPS: 8.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 2.66
- FpuPipeAssignment.Total2: 2.67
- FpuPipeAssignment.Total3: 2.67
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 8 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1
  18:	62 f1 7c 48 5a e9    	vcvtps2pd zmm5,ymm1
  1e:	62 f1 7c 48 5a f1    	vcvtps2pd zmm6,ymm1
  24:	62 f1 7c 48 5a f9    	vcvtps2pd zmm7,ymm1
  2a:	62 71 7c 48 5a c1    	vcvtps2pd zmm8,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 9.32
- APERF: 10.68
- UOPS: 16.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.33
- FpuPipeAssignment.Total2: 5.33
- FpuPipeAssignment.Total3: 5.34
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1
  18:	62 f1 7c 48 5a e9    	vcvtps2pd zmm5,ymm1
  1e:	62 f1 7c 48 5a f1    	vcvtps2pd zmm6,ymm1
  24:	62 f1 7c 48 5a f9    	vcvtps2pd zmm7,ymm1
  2a:	62 71 7c 48 5a c1    	vcvtps2pd zmm8,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 9.21
- APERF: 10.7
- UOPS: 17.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.32
- FpuPipeAssignment.Total2: 5.35
- FpuPipeAssignment.Total3: 5.33
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1
  18:	62 f1 7c 48 5a e9    	vcvtps2pd zmm5,ymm1
  1e:	62 f1 7c 48 5a f1    	vcvtps2pd zmm6,ymm1
  24:	62 f1 7c 48 5a f9    	vcvtps2pd zmm7,ymm1
  2a:	62 71 7c 48 5a c1    	vcvtps2pd zmm8,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 9.21
- APERF: 10.69
- UOPS: 16.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 5.33
- FpuPipeAssignment.Total2: 5.34
- FpuPipeAssignment.Total3: 5.34
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With 16 independent instructions

With unroll_count=100 and no inner loop

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1
  18:	62 f1 7c 48 5a e9    	vcvtps2pd zmm5,ymm1
  1e:	62 f1 7c 48 5a f1    	vcvtps2pd zmm6,ymm1
  24:	62 f1 7c 48 5a f9    	vcvtps2pd zmm7,ymm1
  2a:	62 71 7c 48 5a c1    	vcvtps2pd zmm8,ymm1
  30:	62 71 7c 48 5a c9    	vcvtps2pd zmm9,ymm1
  36:	62 71 7c 48 5a d1    	vcvtps2pd zmm10,ymm1
  3c:	62 71 7c 48 5a d9    	vcvtps2pd zmm11,ymm1
  42:	62 71 7c 48 5a e1    	vcvtps2pd zmm12,ymm1
  48:	62 e1 7c 48 5a c1    	vcvtps2pd zmm16,ymm1
  4e:	62 e1 7c 48 5a c9    	vcvtps2pd zmm17,ymm1
  54:	62 e1 7c 48 5a d1    	vcvtps2pd zmm18,ymm1
  5a:	62 e1 7c 48 5a d9    	vcvtps2pd zmm19,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 18.8
- APERF: 21.32
- UOPS: 32.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 10.67
- FpuPipeAssignment.Total2: 10.67
- FpuPipeAssignment.Total3: 10.66
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=1

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1
  18:	62 f1 7c 48 5a e9    	vcvtps2pd zmm5,ymm1
  1e:	62 f1 7c 48 5a f1    	vcvtps2pd zmm6,ymm1
  24:	62 f1 7c 48 5a f9    	vcvtps2pd zmm7,ymm1
  2a:	62 71 7c 48 5a c1    	vcvtps2pd zmm8,ymm1
  30:	62 71 7c 48 5a c9    	vcvtps2pd zmm9,ymm1
  36:	62 71 7c 48 5a d1    	vcvtps2pd zmm10,ymm1
  3c:	62 71 7c 48 5a d9    	vcvtps2pd zmm11,ymm1
  42:	62 71 7c 48 5a e1    	vcvtps2pd zmm12,ymm1
  48:	62 e1 7c 48 5a c1    	vcvtps2pd zmm16,ymm1
  4e:	62 e1 7c 48 5a c9    	vcvtps2pd zmm17,ymm1
  54:	62 e1 7c 48 5a d1    	vcvtps2pd zmm18,ymm1
  5a:	62 e1 7c 48 5a d9    	vcvtps2pd zmm19,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 18.42
- APERF: 21.37
- UOPS: 33.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 10.66
- FpuPipeAssignment.Total2: 10.68
- FpuPipeAssignment.Total3: 10.67
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=10

Code:

   0:	62 f1 7c 48 5a c1    	vcvtps2pd zmm0,ymm1
   6:	62 f1 7c 48 5a d1    	vcvtps2pd zmm2,ymm1
   c:	62 f1 7c 48 5a d9    	vcvtps2pd zmm3,ymm1
  12:	62 f1 7c 48 5a e1    	vcvtps2pd zmm4,ymm1
  18:	62 f1 7c 48 5a e9    	vcvtps2pd zmm5,ymm1
  1e:	62 f1 7c 48 5a f1    	vcvtps2pd zmm6,ymm1
  24:	62 f1 7c 48 5a f9    	vcvtps2pd zmm7,ymm1
  2a:	62 71 7c 48 5a c1    	vcvtps2pd zmm8,ymm1
  30:	62 71 7c 48 5a c9    	vcvtps2pd zmm9,ymm1
  36:	62 71 7c 48 5a d1    	vcvtps2pd zmm10,ymm1
  3c:	62 71 7c 48 5a d9    	vcvtps2pd zmm11,ymm1
  42:	62 71 7c 48 5a e1    	vcvtps2pd zmm12,ymm1
  48:	62 e1 7c 48 5a c1    	vcvtps2pd zmm16,ymm1
  4e:	62 e1 7c 48 5a c9    	vcvtps2pd zmm17,ymm1
  54:	62 e1 7c 48 5a d1    	vcvtps2pd zmm18,ymm1
  5a:	62 e1 7c 48 5a d9    	vcvtps2pd zmm19,ymm1

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;
VMOVUPD YMM1, [R14]

Show nanoBench command
Results:
- MPERF: 18.42
- APERF: 21.36
- UOPS: 32.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 10.66
- FpuPipeAssignment.Total2: 10.68
- FpuPipeAssignment.Total3: 10.67
- 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 f1 7c 48 5a c0    	vcvtps2pd zmm0,ymm0

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;
VMOVUPD YMM0, [R14]

Show nanoBench command
Results:
- MPERF: 5.19
- APERF: 6.0
- UOPS: 2.0
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.5
- FpuPipeAssignment.Total2: 0.91
- FpuPipeAssignment.Total3: 0.6
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=1000 and unroll_count=10

Code:

   0:	62 f1 7c 48 5a c0    	vcvtps2pd zmm0,ymm0

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;
VMOVUPD YMM0, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- UOPS: 2.1
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.45
- FpuPipeAssignment.Total2: 0.92
- FpuPipeAssignment.Total3: 0.63
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

With loop_count=100 and unroll_count=100

Code:

   0:	62 f1 7c 48 5a c0    	vcvtps2pd zmm0,ymm0

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;
VMOVUPD YMM0, [R14]

Show nanoBench command
Results:
- MPERF: 5.17
- APERF: 6.0
- UOPS: 2.01
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.48
- FpuPipeAssignment.Total2: 0.91
- FpuPipeAssignment.Total3: 0.61
- FpuPipeAssignment.Total4: 0.0
- FpuPipeAssignment.Total5: 0.0
- DIV_CYCLES: 0.0

VCVTPS2PD (ZMM, YMM) - 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