INVLPG (M8)

Operands

• Operand 1 (r): Memory

Available performance data

• Alder Lake-P
• Alder Lake-E
• Rocket Lake
• Tiger Lake
• Ice Lake
• Cascade Lake
• Cannon Lake
• Skylake-X
• Coffee Lake
• Kaby Lake
• Skylake
• Broadwell
• Haswell
• Ivy Bridge
• Sandy Bridge
• Westmere
• Nehalem
• Wolfdale
• Conroe
• Tremont
• Goldmont Plus
• Goldmont
• Airmont
• Bonnell
• AMD Zen 4
• AMD Zen 3
• AMD Zen 2
• AMD Zen+

Alder Lake-P

• Measurements
• Throughput
  • Computed from the port usage: 7.00 (if an indexed addressing mode is used: 6.67)
  • Measured (loop): 223.75 (if an indexed addressing mode is used: 223.72)
  • Measured (unrolled): 223.65 (if an indexed addressing mode is used: 223.69)
• Number of μops
  • Executed: 42
  • Retire slots: 40
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 42
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 5*p0+3*p0156B+2*p056+7*p06+6*p1+2*p15B+5*p49+7*p5+5*p78 (if an indexed addressing mode is used: 5*p0+8*p056+7*p06+6*p1+5*p49+5*p78)

Alder Lake-E

• Measurements
• Throughput
  • Measured (loop): 97.53
  • Measured (unrolled): 98.00
• Number of μops
  • Executed: 20
  • Microcode Sequencer (MS): 19
  • Requires the complex decoder

Rocket Lake

• Measurements
• Throughput
  • Computed from the port usage: 9.00
  • Measured (loop): 260.43
  • Measured (unrolled): 257.60
• Number of μops
  • Executed: 45
  • Retire slots: 46
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 48
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 5*p0+4*p0156+13*p06+6*p1+1*p23+5*p49+6*p5+5*p78

Tiger Lake

• Measurements
• Throughput
  • Computed from the port usage: 9.00
  • Measured (loop): 259.98
  • Measured (unrolled): 257.54
• Number of μops
  • Executed: 45
  • Retire slots: 46
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 48
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 5*p0+1*p015+3*p0156+13*p06+6*p1+1*p23+5*p49+6*p5+5*p78

Ice Lake

• Measurements
• Throughput
  • Computed from the port usage: 8.50
  • Measured (loop): 217.90
  • Measured (unrolled): 216.13
• Number of μops
  • Executed: 43
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 6*p0+4*p0156+11*p06+6*p1+5*p49+6*p5+5*p78

Cascade Lake

• Measurements
• Throughput
  • Computed from the port usage: 9.50
  • Measured (loop): 228.92
  • Measured (unrolled): 230.50
• Number of μops
  • Executed: 47
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 7*p0+3*p0156+12*p06+7*p1+2*p23+3*p237+5*p4+8*p5

Cannon Lake

• Measurements
• Throughput
  • Computed from the port usage: 8.25
  • Measured (loop): 215.03
  • Measured (unrolled): 213.12
• Number of μops
  • Executed: 43
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 4*p0+4*p0156+11*p06+8*p1+2*p23+3*p237+5*p4+6*p5

Skylake-X

• Measurements
• Throughput
  • Computed from the port usage: 9.50
  • Measured (loop): 224.90
  • Measured (unrolled): 231.00
• Number of μops
  • Executed: 47
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 7*p0+3*p0156+12*p06+7*p1+2*p23+3*p237+5*p4+8*p5

Coffee Lake

• Measurements
• Throughput
  • Computed from the port usage: 9.50
  • Measured (loop): 213.28
  • Measured (unrolled): 210.75
• Number of μops
  • Executed: 47
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 7*p0+3*p0156+12*p06+7*p1+2*p23+3*p237+5*p4+8*p5

Kaby Lake

• Measurements
• Throughput
  • Computed from the port usage: 9.50
  • Measured (loop): 213.12
  • Measured (unrolled): 210.94
• Number of μops
  • Executed: 47
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 7*p0+3*p0156+12*p06+7*p1+2*p23+3*p237+5*p4+8*p5

Skylake

• Measurements
• Throughput
  • Computed from the port usage: 9.50
  • Measured (loop): 213.17
  • Measured (unrolled): 211.13
• Number of μops
  • Executed: 47
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 7*p0+3*p0156+12*p06+7*p1+2*p23+3*p237+5*p4+8*p5

Broadwell

• Measurements
• Throughput
  • Computed from the port usage: 11.00
  • Measured (loop): 209.02
  • Measured (unrolled): 206.75
• Number of μops
  • Executed: 49
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 7*p0+3*p0156+15*p06+6*p1+2*p23+3*p237+5*p4+8*p5

Haswell

• Measurements
• Throughput
  • Computed from the port usage: 10.50
  • Measured (loop): 210.02
  • Measured (unrolled): 207.84
• Number of μops
  • Executed: 49
  • Retire slots: 42
  • Decoded (MITE): 0
  • Microcode Sequencer (MS): 44
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 7*p0+3*p0156+14*p06+7*p1+2*p23+3*p237+5*p4+8*p5

Ivy Bridge

• Measurements
• Throughput
  • Computed from the port usage: 19.00
  • Measured (loop): 238.70
  • Measured (unrolled): 236.56
• Number of μops
  • Executed: 49
  • Retire slots: 45
  • Decoded (MITE): 1
  • Microcode Sequencer (MS): 46
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 10*p0+1*p015+10*p1+5*p23+4*p4+19*p5

Sandy Bridge

• Measurements
• Throughput
  • Computed from the port usage: 18.00
  • Measured (loop): 235.82
  • Measured (unrolled): 233.63
• Number of μops
  • Executed: 49
  • Retire slots: 45
  • Decoded (MITE): 1
  • Microcode Sequencer (MS): 46
  • Requires the complex decoder (no other instruction can be decoded with simple decoders in the same cycle)
• Port usage: 11*p0+1*p015+10*p1+5*p23+4*p4+18*p5

Westmere

• Measurements
• Throughput
  • Computed from the port usage: 16.00
  • Measured (loop): 203.80
  • Measured (unrolled): 203.00
• Number of μops
  • Executed: 48
  • Retire slots: 45
  • Microcode Sequencer (MS): 133
  • Requires the complex decoder
• Port usage: 11*p0+5*p015+8*p1+2*p2+3*p3+3*p4+16*p5

Nehalem

• Measurements
• Throughput
  • Computed from the port usage: 16.00
  • Measured (loop): 211.80
  • Measured (unrolled): 211.00
• Number of μops
  • Executed: 49
  • Retire slots: 45
  • Microcode Sequencer (MS): 141
  • Requires the complex decoder
• Port usage: 8*p0+4*p015+11*p1+2*p2+4*p3+4*p4+16*p5

Wolfdale

• Measurements
• Throughput
  • Computed from the port usage: 33.00
  • Measured (loop): 250.17
  • Measured (unrolled): 249.09
• Number of μops
  • Executed: 57
• Port usage: 14*p0+11*p1+7*p2+6*p3+6*p4+33*p5

Conroe

• Measurements
• Throughput
  • Computed from the port usage: 33.00
  • Measured (loop): 248.70
  • Measured (unrolled): 246.48
• Number of μops
  • Executed: 60
• Port usage: 13*p0+15*p1+7*p2+6*p3+6*p4+33*p5

Tremont

• Measurements
• Throughput
  • Measured (loop): 72.78
  • Measured (unrolled): 72.00
• Number of μops
  • Executed: 16
  • Microcode Sequencer (MS): 15
  • Requires the complex decoder

Goldmont Plus

• Measurements
• Throughput
  • Measured (loop): 60.03
  • Measured (unrolled): 59.75
• Number of μops
  • Executed: 18
  • Microcode Sequencer (MS): 18
  • Requires the complex decoder

Goldmont

• Measurements
• Throughput
  • Measured (loop): 61.00
  • Measured (unrolled): 61.00
• Number of μops
  • Executed: 21
  • Microcode Sequencer (MS): 21
  • Requires the complex decoder

Airmont

• Measurements
• Throughput
  • Measured (loop): 71.44
  • Measured (unrolled): 70.87
• Number of μops
  • Executed: 21
  • Microcode Sequencer (MS): 21
  • Requires the complex decoder

Bonnell

• Measurements
• Throughput
  • Measured (loop): 59.04
  • Measured (unrolled): 59.00
• Number of μops
  • Executed: 20
  • Microcode Sequencer (MS): 20
  • Requires the complex decoder

AMD Zen 4

• Measurements
• Throughput
  • Measured (loop): 121.67
  • Measured (unrolled): 118.00
• Number of μops
  • Executed: 26

AMD Zen 3

• Measurements
• Throughput
  • Measured (loop): 118.90
  • Measured (unrolled): 117.97
• Number of μops
  • Executed: 26
• Documentation
• Number of μops: ucode

AMD Zen 2

• Measurements
• Throughput
  • Measured (loop): 126.80
  • Measured (unrolled): 126.00
• Number of μops
  • Executed: 24
• Documentation
• Number of μops: ucode

AMD Zen+

• Measurements
• Throughput
  • Measured (loop): 126.90
  • Measured (unrolled): 126.00
• Number of μops
  • Executed: 24
• Documentation
• Number of μops: ucode