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

SBFIZ (32-bit)

Test 1: uops

Code:

  sbfiz w0, w0, #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)03mmu table walk instruction (07)l2 tlb miss data (0b)18191e1f3f4d51schedule 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 miss (a1)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
1004103580000006186225100010001000169161103510357283868100010001000103541111001100000073241119371000100010361036103610361036
1004103580000006186225100010001000169161103510357283868100010001000103541111001100000073141119371000100010361036103610361036
1004103580000006186225100010001000169161103510357283868100010001000103541111001100000073141119371000100010361036103610361036
10041035800002107586225100010001000169161103510357283868100010001000103541111001100000073141119371000100010361036103610361036
1004103580000006186225100010001153179521108210357283868100011691000103541111001100000073141119371000100010361036103610361036
100410358000000393862251000102211531891911035103572838681000100010001035411110011000004273141119371000100010361036103610361036
1004103570000006186225100010001000169161103510357283868100010001000103541111001100000073141119371000100010361036103610361036
1004103580000006186225100010251000169161103510357283868100011711000103541211001100000144073141119371000100010361036103610361036
1004103580000006186225100010001000169161103510357283868100010001169108141111001100000119073141119371000100010361036108110361036
10041080810000075862251000100010001691611035103572838681000100010001035411110011000000731411110011000100010821036103610361036

Test 2: Latency 1->2

Code:

  sbfiz w0, w0, #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)031e3f4d51schedule 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)9faccfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
10204100357548619877251010010100101008866414969551003510035858038722101001020010200100354111102011009910010100100371013711994110000101001003610036100361003610036
1020410035750829877251010010100101008866404969551003510035858038722101001020010200100354111102011009910010100100371013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866404969551003510035858038722101001020010200100354111102011009910010100100371013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866404969551003510035858038722101001020010200100354111102011009910010100100371013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866404969551003510035858038722101001020010200100354111102011009910010100100371013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866404969551003510035858038722101001020010200100354111102011009910010100100071013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866414969551003510035858038722101001020010200100354111102011009910010100100071013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866414969551003510035858038722101001020010200100354111102011009910010100100071013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866404969551003510035858038722101001020010200100354111102011009910010100100071013711994110000101001003610036100361003610036
1020410035750619877251010010100101008866404969551003510035858038722101001020010200100354111102011009910010100100071013711994110000101001003610036100361003610036

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0035

retire uop (01)cycle (02)031e3f4d51schedule 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 cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
10024100357502759863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010100064044133994010000100101003610036100361003610036
1002410035760619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010100064034133994010000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010102064034133998110000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010106064034133994010000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010107064034133994010000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010102364034133994010000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010100064034133994010000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010100064034133994010000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010103064034133994010000100101003610036100361003610036
1002410035750619863251001010010100108878414969551003510035860238740100101002010020100354111100211091010010102064034133994010000100101003610036100361003610036

Test 3: throughput

Count: 8

Code:

  sbfiz w0, w8, #3, #7
  sbfiz w1, w8, #3, #7
  sbfiz w2, w8, #3, #7
  sbfiz w3, w8, #3, #7
  sbfiz w4, w8, #3, #7
  sbfiz w5, w8, #3, #7
  sbfiz w6, w8, #3, #7
  sbfiz w7, w8, #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)mmu table walk data (08)l2 tlb miss instruction (0a)l2 tlb miss data (0b)18191e1f3f51schedule 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 access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
802041341410100000000562780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000000001115119016001338780036801001339113391133911339113391
80204133901000000000028278013680136801484007101491031013390133903326633368014880264802641339039118020110099100801001000000001411115119016001338780036801001339113391133911339113391
802041339010000000000282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000000001115119016001338780036801001339113391133911339113391
80204133901000000000032927801368013680148400710149103101339013390332663336801488026480264133903911802011009910080100100000000841115119016001338780036801001339113391133911339113391
8020413390101000000002827801368013680148400710149103101339013390332663336801488026480264133903911802011009910080100100000000181115119016001338780036801001339113391133911339113391
802041339010000000000282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000000001115119016001338780036801001339113391133911339113391
80204133901000000000070278013680136801484007101491031013390133903326633368014880264802641339039118020110099100801001000000001291115119016001338780036801001339113391133911339113391
802041339010000000000282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000000001115119016001338780036801001339113391133911339113391
802041339010000000000282780136801368014840071014910310133901339033266333680148802648026413390391180201100991008010010000000001115119016001338780036801001339113391133911339113391
802041339010000000000282780136802648014840071014910310133901339033266333680148802648026413390391180201100991008010010000000001115119016001338780036801001339113391133911339113391

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03mmu table walk instruction (07)l2 tlb miss data (0b)18191e1f3f51schedule 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)dadbddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
8002413387100000000772580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010000502011951111336880000800101337213372133721337213372
8002413371100000000352580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010000502011910111336880000800101337213372133721337213372
80024133711000000001002580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010000502011930111336880000800101337213372133721337213372
80024133711000000001192580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010023502011940111336880000800101337213372133721337213372
800241337110000000010225800108001080010400050049102911337113371333033348800108002080020133713911800211091080010100473502011920111336880000800101337213372133721337213372
80024133711000000005102580010800108001040005014910291133711337133303334880010800208002013371391180021109108001010000502011940111336880000800101337213372133721337213372
8002413371100000000352580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010000502011940511336880000800101337213372133721337213372
80024133711000000001802580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010000502011920111336880000800101337213372133721337213372
8002413371100000000352580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010010502011940111336880000800101337213372133721337213372
8002413371100000000582580010800108001040005004910291133711337133303334880010800208002013371391180021109108001010000502011910111336880000800101337213372133721337213372