BZHI (R32, M32, R32)

Experiment 1

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instructions: MOVSX R8, R8D;XOR R14, R8;XOR R14, R8;XOR R14, R8;XOR R14, R8
Chain latency: 5

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 63 c0             	movsxd r8,r8d
   8:	4d 31 c6             	xor    r14,r8
   b:	4d 31 c6             	xor    r14,r8
   e:	4d 31 c6             	xor    r14,r8
  11:	4d 31 c6             	xor    r14,r8

Init:

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

Show nanoBench command
Results:
- MPERF: 8.67
- APERF: 9.99
- UOPS: 7.0

Latency operand 2 → 1 (address, index register): 5

Experiment 1

Instruction: BZHI R8D, dword ptr [R14+R13], R9D
Chain instructions: MOVSX R8, R8D;XOR R13, R8;XOR R13, R8;XOR R13, R8;XOR R13, R8
Chain latency: 5

Code:

   0:	c4 02 30 f5 04 2e    	bzhi   r8d,DWORD PTR [r14+r13*1],r9d
   6:	4d 63 c0             	movsxd r8,r8d
   9:	4d 31 c5             	xor    r13,r8
   c:	4d 31 c5             	xor    r13,r8
   f:	4d 31 c5             	xor    r13,r8
  12:	4d 31 c5             	xor    r13,r8

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 8.78
- APERF: 9.99
- UOPS: 7.0

Latency operand 2 → 1 (memory): ≤7

Experiment 1

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instructions: MOVSX R12, R8D;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
Chain latency: ≥5

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 63 e0             	movsxd r12,r8d
   8:	4d 63 e4             	movsxd r12,r12d
   b:	4d 63 e4             	movsxd r12,r12d
   e:	4d 63 e4             	movsxd r12,r12d
  11:	45 89 26             	mov    DWORD PTR [r14],r12d

Init:

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

Show nanoBench command
Results:
- MPERF: 10.54
- APERF: 11.99
- UOPS: 7.0

Latency operand 2 → 4 (address, base register): 5

Experiment 1

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instruction: CMOVZ R14, R14
Chain latency: 1

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 44 f6          	cmove  r14,r14

Init:

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

Show nanoBench command
Results:
- MPERF: 5.38
- APERF: 6.0
- UOPS: 3.0

Experiment 2

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instruction: CMOVS R14, R14
Chain latency: 1

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 48 f6          	cmovs  r14,r14

Init:

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

Show nanoBench command
Results:
- MPERF: 5.27
- APERF: 6.0
- UOPS: 3.0

Experiment 3

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instruction: CMOVO R14, R14
Chain latency: 1

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 40 f6          	cmovo  r14,r14

Init:

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

Show nanoBench command
Results:
- MPERF: 5.27
- APERF: 6.0
- UOPS: 3.0

Experiment 4

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instruction: CMOVC R14, R14
Chain latency: 1

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 42 f6          	cmovb  r14,r14

Init:

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

Show nanoBench command
Results:
- MPERF: 5.21
- APERF: 6.0
- UOPS: 3.0

Latency operand 2 → 4 (address, index register): 5

Experiment 1

Instruction: BZHI R8D, dword ptr [R14+R13], R9D
Chain instruction: CMOVZ R13, R13
Chain latency: 1

Code:

   0:	c4 02 30 f5 04 2e    	bzhi   r8d,DWORD PTR [r14+r13*1],r9d
   6:	4d 0f 44 ed          	cmove  r13,r13

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 5.27
- APERF: 6.0
- UOPS: 3.0

Experiment 2

Instruction: BZHI R8D, dword ptr [R14+R13], R9D
Chain instruction: CMOVS R13, R13
Chain latency: 1

Code:

   0:	c4 02 30 f5 04 2e    	bzhi   r8d,DWORD PTR [r14+r13*1],r9d
   6:	4d 0f 48 ed          	cmovs  r13,r13

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 5.27
- APERF: 6.0
- UOPS: 3.0

Experiment 3

Instruction: BZHI R8D, dword ptr [R14+R13], R9D
Chain instruction: CMOVO R13, R13
Chain latency: 1

Code:

   0:	c4 02 30 f5 04 2e    	bzhi   r8d,DWORD PTR [r14+r13*1],r9d
   6:	4d 0f 40 ed          	cmovo  r13,r13

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 5.33
- APERF: 6.0
- UOPS: 3.0

Experiment 4

Instruction: BZHI R8D, dword ptr [R14+R13], R9D
Chain instruction: CMOVC R13, R13
Chain latency: 1

Code:

   0:	c4 02 30 f5 04 2e    	bzhi   r8d,DWORD PTR [r14+r13*1],r9d
   6:	4d 0f 42 ed          	cmovb  r13,r13

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 5.27
- APERF: 6.0
- UOPS: 3.0

Latency operand 2 → 4 (memory): ≤7

Experiment 1

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instructions: CMOVZ R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
Chain latency: ≥6

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 44 e4          	cmove  r12,r12
   9:	4d 63 e4             	movsxd r12,r12d
   c:	4d 63 e4             	movsxd r12,r12d
   f:	4d 63 e4             	movsxd r12,r12d
  12:	4d 63 e4             	movsxd r12,r12d
  15:	45 89 26             	mov    DWORD PTR [r14],r12d

Init:

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

Show nanoBench command
Results:
- MPERF: 11.45
- APERF: 13.01
- UOPS: 8.0

Experiment 2

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instructions: CMOVS R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
Chain latency: ≥6

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 48 e4          	cmovs  r12,r12
   9:	4d 63 e4             	movsxd r12,r12d
   c:	4d 63 e4             	movsxd r12,r12d
   f:	4d 63 e4             	movsxd r12,r12d
  12:	4d 63 e4             	movsxd r12,r12d
  15:	45 89 26             	mov    DWORD PTR [r14],r12d

Init:

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

Show nanoBench command
Results:
- MPERF: 11.39
- APERF: 13.01
- UOPS: 8.0

Experiment 3

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instructions: CMOVO R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
Chain latency: ≥6

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 40 e4          	cmovo  r12,r12
   9:	4d 63 e4             	movsxd r12,r12d
   c:	4d 63 e4             	movsxd r12,r12d
   f:	4d 63 e4             	movsxd r12,r12d
  12:	4d 63 e4             	movsxd r12,r12d
  15:	45 89 26             	mov    DWORD PTR [r14],r12d

Init:

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

Show nanoBench command
Results:
- MPERF: 11.39
- APERF: 13.01
- UOPS: 8.0

Experiment 4

Instruction: BZHI R8D, dword ptr [R14], R9D
Chain instructions: CMOVC R12, R12;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;MOVSX R12, R12d;mov [R14], R12D
Chain latency: ≥6

Code:

   0:	c4 42 30 f5 06       	bzhi   r8d,DWORD PTR [r14],r9d
   5:	4d 0f 42 e4          	cmovb  r12,r12
   9:	4d 63 e4             	movsxd r12,r12d
   c:	4d 63 e4             	movsxd r12,r12d
   f:	4d 63 e4             	movsxd r12,r12d
  12:	4d 63 e4             	movsxd r12,r12d
  15:	45 89 26             	mov    DWORD PTR [r14],r12d

Init:

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

Show nanoBench command
Results:
- MPERF: 11.33
- APERF: 13.01
- UOPS: 8.0

Latency operand 3 → 1: 1

Experiment 1

Instruction: BZHI R9D, dword ptr [R14], R8D
Chain instructions: MOVSX R8, R9D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
Chain latency: 5

Code:

   0:	c4 42 38 f5 0e       	bzhi   r9d,DWORD PTR [r14],r8d
   5:	4d 63 c1             	movsxd r8,r9d
   8:	4d 63 c0             	movsxd r8,r8d
   b:	4d 63 c0             	movsxd r8,r8d
   e:	4d 63 c0             	movsxd r8,r8d
  11:	4d 63 c0             	movsxd r8,r8d

Init:

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

Show nanoBench command
Results:
- MPERF: 5.16
- APERF: 6.0
- UOPS: 7.0

Latency operand 3 → 4: 1

Experiment 1

Instruction: BZHI R9D, dword ptr [R14], R8D
Chain instructions: CMOVZ R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
Chain latency: 6

Code:

   0:	c4 42 38 f5 0e       	bzhi   r9d,DWORD PTR [r14],r8d
   5:	45 0f 44 ff          	cmove  r15d,r15d
   9:	4d 63 c7             	movsxd r8,r15d
   c:	4d 63 c0             	movsxd r8,r8d
   f:	4d 63 c0             	movsxd r8,r8d
  12:	4d 63 c0             	movsxd r8,r8d
  15:	4d 63 c0             	movsxd r8,r8d

Init:

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

Show nanoBench command
Results:
- MPERF: 6.12
- APERF: 7.01
- UOPS: 8.0

Experiment 2

Instruction: BZHI R9D, dword ptr [R14], R8D
Chain instructions: CMOVS R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
Chain latency: 6

Code:

   0:	c4 42 38 f5 0e       	bzhi   r9d,DWORD PTR [r14],r8d
   5:	45 0f 48 ff          	cmovs  r15d,r15d
   9:	4d 63 c7             	movsxd r8,r15d
   c:	4d 63 c0             	movsxd r8,r8d
   f:	4d 63 c0             	movsxd r8,r8d
  12:	4d 63 c0             	movsxd r8,r8d
  15:	4d 63 c0             	movsxd r8,r8d

Init:

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

Show nanoBench command
Results:
- MPERF: 6.12
- APERF: 7.01
- UOPS: 8.0

Experiment 3

Instruction: BZHI R9D, dword ptr [R14], R8D
Chain instructions: CMOVO R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
Chain latency: 6

Code:

   0:	c4 42 38 f5 0e       	bzhi   r9d,DWORD PTR [r14],r8d
   5:	45 0f 40 ff          	cmovo  r15d,r15d
   9:	4d 63 c7             	movsxd r8,r15d
   c:	4d 63 c0             	movsxd r8,r8d
   f:	4d 63 c0             	movsxd r8,r8d
  12:	4d 63 c0             	movsxd r8,r8d
  15:	4d 63 c0             	movsxd r8,r8d

Init:

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

Show nanoBench command
Results:
- MPERF: 6.12
- APERF: 7.01
- UOPS: 8.0

Experiment 4

Instruction: BZHI R9D, dword ptr [R14], R8D
Chain instructions: CMOVC R15D, R15D;MOVSX R8, R15D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D;MOVSX R8, R8D
Chain latency: 6

Code:

   0:	c4 42 38 f5 0e       	bzhi   r9d,DWORD PTR [r14],r8d
   5:	45 0f 42 ff          	cmovb  r15d,r15d
   9:	4d 63 c7             	movsxd r8,r15d
   c:	4d 63 c0             	movsxd r8,r8d
   f:	4d 63 c0             	movsxd r8,r8d
  12:	4d 63 c0             	movsxd r8,r8d
  15:	4d 63 c0             	movsxd r8,r8d

Init:

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

Show nanoBench command
Results:
- MPERF: 6.06
- APERF: 7.01
- UOPS: 8.0

BZHI (R32, M32, R32) - Latency

Operands

Latency operand 2 → 1 (address, base register): 5

Latency operand 2 → 1 (address, index register): 5

Latency operand 2 → 1 (memory): ≤7

Latency operand 2 → 4 (address, base register): 5

Latency operand 2 → 4 (address, index register): 5

Latency operand 2 → 4 (memory): ≤7

Latency operand 3 → 1: 1

Latency operand 3 → 4: 1

Latency operand 2 → 1 (address, base register): 5

Experiment 1

Latency operand 2 → 1 (address, index register): 5

Experiment 1

Latency operand 2 → 1 (memory): ≤7

Experiment 1

Latency operand 2 → 4 (address, base register): 5

Experiment 1

Experiment 2

Experiment 3

Experiment 4

Latency operand 2 → 4 (address, index register): 5

Experiment 1

Experiment 2

Experiment 3

Experiment 4

Latency operand 2 → 4 (memory): ≤7

Experiment 1

Experiment 2

Experiment 3

Experiment 4

Latency operand 3 → 1: 1

Experiment 1

Latency operand 3 → 4: 1

Experiment 1

Experiment 2

Experiment 3

Experiment 4