VPCOMPRESSD_Z (YMM, K, YMM)

Experiment 1

Instruction: VPCOMPRESSD YMM0 {K1}{z}, YMM1
Chain instruction: VPMOVQ2M K1, YMM0
Chain latency: 4

Code:

   0:	62 f2 7d a9 8b c8    	vpcompressd ymm0{k1}{z},ymm1
   6:	62 f2 fe 28 39 c8    	vpmovq2m k1,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- MPERF: 10.34
- APERF: 12.0
- UOPS: 3.0

Experiment 2

Instruction: VPCOMPRESSD YMM0 {K1}{z}, YMM1
Chain instruction: VPTESTNMQ K1 {K1}, YMM0, YMM0
Chain latency: 4

Code:

   0:	62 f2 7d a9 8b c8    	vpcompressd ymm0{k1}{z},ymm1
   6:	62 f2 fe 29 27 c8    	vptestnmq k1{k1},ymm0,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM1, YMM1, YMM1

Show nanoBench command
Results:
- MPERF: 10.26
- APERF: 12.0
- UOPS: 3.0

Experiment 3 (source registers initialized by an instruction of the same kind)

Instruction: VPCOMPRESSD YMM0 {K1}{z}, YMM1
Chain instruction: VPMOVQ2M K1, YMM0
Chain latency: 4

Code:

   0:	62 f2 7d a9 8b c8    	vpcompressd ymm0{k1}{z},ymm1
   6:	62 f2 fe 28 39 c8    	vpmovq2m k1,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM1, YMM1, YMM1;
VPCOMPRESSD YMM1  {K1}{z}, YMM0

Show nanoBench command
Results:
- MPERF: 10.34
- APERF: 12.01
- UOPS: 3.0

Experiment 4 (source registers initialized by an instruction of the same kind)

Instruction: VPCOMPRESSD YMM0 {K1}{z}, YMM1
Chain instruction: VPTESTNMQ K1 {K1}, YMM0, YMM0
Chain latency: 4

Code:

   0:	62 f2 7d a9 8b c8    	vpcompressd ymm0{k1}{z},ymm1
   6:	62 f2 fe 29 27 c8    	vptestnmq k1{k1},ymm0,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM1, YMM1, YMM1;
VPCOMPRESSD YMM1  {K1}{z}, YMM0

Show nanoBench command
Results:
- MPERF: 10.34
- APERF: 12.01
- UOPS: 3.0

Experiment 1

Instruction: VPCOMPRESSD YMM1 {K1}{z}, YMM0
Chain instructions: VANDPD YMM0, YMM1, YMM1;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	62 f2 7d a9 8b c1    	vpcompressd ymm1{k1}{z},ymm0
   6:	c5 f5 54 c1          	vandpd ymm0,ymm1,ymm1
   a:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
   e:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  12:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  16:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1a:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1e:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM0, YMM0, YMM0

Show nanoBench command
Results:
- MPERF: 9.56
- APERF: 11.19
- UOPS: 9.0

Experiment 2

Instruction: VPCOMPRESSD YMM1 {K1}{z}, YMM0
Chain instructions: VPAND YMM0, YMM1, YMM1;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	62 f2 7d a9 8b c1    	vpcompressd ymm1{k1}{z},ymm0
   6:	c5 f5 db c1          	vpand  ymm0,ymm1,ymm1
   a:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
   e:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  12:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  16:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  1a:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  1e:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM0, YMM0, YMM0

Show nanoBench command
Results:
- MPERF: 9.64
- APERF: 11.03
- UOPS: 9.0

Experiment 3 (source registers initialized by an instruction of the same kind)

Instruction: VPCOMPRESSD YMM1 {K1}{z}, YMM0
Chain instructions: VANDPD YMM0, YMM1, YMM1;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0;VANDPD YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	62 f2 7d a9 8b c1    	vpcompressd ymm1{k1}{z},ymm0
   6:	c5 f5 54 c1          	vandpd ymm0,ymm1,ymm1
   a:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
   e:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  12:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  16:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1a:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0
  1e:	c5 fd 54 c0          	vandpd ymm0,ymm0,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VPCOMPRESSD YMM0  {K1}{z}, YMM1

Show nanoBench command
Results:
- MPERF: 9.64
- APERF: 11.14
- UOPS: 9.0

Experiment 4 (source registers initialized by an instruction of the same kind)

Instruction: VPCOMPRESSD YMM1 {K1}{z}, YMM0
Chain instructions: VPAND YMM0, YMM1, YMM1;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0;VPAND YMM0, YMM0, YMM0
Chain latency: 7

Code:

   0:	62 f2 7d a9 8b c1    	vpcompressd ymm1{k1}{z},ymm0
   6:	c5 f5 db c1          	vpand  ymm0,ymm1,ymm1
   a:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
   e:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  12:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  16:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  1a:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0
  1e:	c5 fd db c0          	vpand  ymm0,ymm0,ymm0

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS YMM0, YMM0, YMM0;
VPCOMPRESSD YMM0  {K1}{z}, YMM1

Show nanoBench command
Results:
- MPERF: 9.79
- APERF: 11.25
- UOPS: 9.0

VPCOMPRESSD_Z (YMM, K, YMM) - Latency

Operands

Latency operand 2 → 1: 8

Latency operand 3 → 1: 4

Latency operand 2 → 1: 8

Experiment 1

Experiment 2

Experiment 3 (source registers initialized by an instruction of the same kind)

Experiment 4 (source registers initialized by an instruction of the same kind)

Latency operand 3 → 1: 4

Experiment 1

Experiment 2

Experiment 3 (source registers initialized by an instruction of the same kind)

Experiment 4 (source registers initialized by an instruction of the same kind)