Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

UBFIZ (64-bit)

Test 1: uops

Code:

  ubfiz x0, x0, #3, #7
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

retire uop (01)cycle (02)031e3f4d51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)606d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst int alu (97)l1d tlb access (a0)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
10041035706186225100010001000169160103510357283868100010001000103541111001100000073341119371000100010361036103610361036
10041035706186225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035706186225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035706186225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035706186225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035706186225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035806186225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035806186225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
100410358014986225100010001000169160103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035808986225100010001000169160103510357283868100010001000103541111001100000673141119371000100010361036103610361036

Test 2: Latency 1->2

Code:

  ubfiz x0, x0, #3, #7
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0035

retire uop (01)cycle (02)031e1f3f4d51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)60696a6b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
102041003575458861987725101661010010100886641497001010035100358584387221010010200102001003541111020110099100101001001071013711994110000101001003610036100361003610036
102041003575153061987725101001010010100886640496955010035100358580387221010010200102001003541111020110099100101001000371013711994110000101001003610036100361003610036
1020410035750061987725101001010010100886641496955010035100728580387221010010200102001003541111020110099100101001001071013711994110000101001003610036100361003610036
1020410035750061987725101001010010100886641496955010035100358580387221010010200102001003541111020110099100101001001071013711994110000101001003610036100361003610036
1020410035750061987725101001010010100886640496955010035100358580387221010010200102001003541111020110099100101001000071013711994110000101001003610036100361003610036
1020410035750061987725101001010010100886640496955010035100358580387221010010200102001003541111020110099100101001001671013711994110000101001003610036100361003610036
10204100357500103987725101001010010100886640496955010035100358580387221010010200102001003541111020110099100101001000071013711994110000101001003610036100361003610036
1020410035750061987725101001010010100886640496955010035100358580387221010010200102001003541111020110099100101001000071013711994110000101001003610036100361003610036
10204100357500536987725101001010010100886640496955010035100358580387221010010200102001003541111020110099100101001000071013711994110000101001003610036100361003610036
1020410035750061987725101001010010100886640496955010035100358580387221010010200102001003541111020110099100101001000071013711994110000101001003610036100361003610036

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0035

retire uop (01)cycle (02)03l2 tlb miss data (0b)18191e1f3f4d51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)60696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d tlb miss (a1)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
1002410035750002406198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
100241003575000006198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
100241003575000006198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
100241003575000006198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
100241003575000006198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
100241003575000006198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
100241003575000006198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
10024100357500027306198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000064034133994010000100101003610036100361003610036
1002410035750010010398632510010100101001088784149695510035100358602387401016710020100201003541111002110910100101000064034133994010000100101003610036100361003610036
100241003575100006198632510010100101001088784049695510035100358602387401001010020100201003541111002110910100101000366234133994010000100101003610036100361003610036

Test 3: throughput

Count: 8

Code:

  ubfiz x0, x8, #3, #7
  ubfiz x1, x8, #3, #7
  ubfiz x2, x8, #3, #7
  ubfiz x3, x8, #3, #7
  ubfiz x4, x8, #3, #7
  ubfiz x5, x8, #3, #7
  ubfiz x6, x8, #3, #7
  ubfiz x7, x8, #3, #7
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.1674

retire uop (01)cycle (02)03mmu table walk instruction (07)l2 tlb miss instruction (0a)l2 tlb miss data (0b)1e3f51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)60696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d tlb miss (a1)ld unit uop (a6)l1d cache writeback (a8)acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
802041341310011012282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391
80204133901001100282780136801368014840071004910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391
80204133901011100282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391
802041339010011166282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391
802041339010011075282780136801368014840071004910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391
80204133901011100282780136801368014840071004910310133901339033266333680148802648026413390392180201100991008010010000001115119116111338780036801001339113391133911339113391
80204133901001100282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391
80204133901001100282780136801368014840071004910310133901339033266333680148802648026413390391180201100991008010010000191115119116111338780036801001339113391133911339113391
80204133901001100282780136801368014840071004910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391
80204133901001100282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000001115119116111338780036801001339113391133911339113391

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.1671

retire uop (01)cycle (02)03mmu table walk data (08)18191e3f51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)5f60696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d cache writeback (a8)branch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
80024133871000000352580010800108001040005041491029113371133713330333488001080020800201337139118002110910800101000005021719241336880000800101337213372133721337213372
80024133711000000352580010800108001040005071491029113371133713330333488001080020800201337139118002110910800101000005022419241336880000800101337213372133721337213372
80024133711000000352580010800108001040005071491029113371133713330333488001080020800201337139118002110910800101000005022419421336880000800101337213372133721337213372
80024133711000120352580010800108001040005071491029113371133713330333488001080020800201337139118002110910800101000005042419241336880000800101337213372133721337213372
80024133711000000352580010800108001040005091491029113371133713330333488001080020800201337139118002110910800101000005021219261336880000800101337213372133721337213372
80024133711000000352580010800108001040005081491029113371133713330333488001080020800201337139118002110910800101000005022419421336880000800101337213372133721337213372
80024133711000000352580010800108001040005071491029113371133713330333488001080020800201337139118002110910800101000005022419421336880000800101337213372133721337213372
80024133711000000352580010800108001040005081491029113371133713330333488001080020800201337139118002110910800101000005022419421336880000800101337213372133721337213372
80024133711000000352580010800108001040005081491029113371133713330333488001080020800201337139118002110910800101000005021219241336880000800101337213372133721337213372
80024133711000000352580010800108001040005081491029113371133713330333488001080020800201337139118002110910800101001005022419241336880000800101337213372133721337213372