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

FCVTZS (scalar, integer, S to W)

Test 1: uops

Code:

  fcvtzs w0, s0
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 2.000

Issues: 3.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 2.000

retire uop (01)cycle (02)031e3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map simd uop (7e)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst int alu (97)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
2004541404325300010002000200018000052254154124832742000200020005415411110011000007321622538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007321622538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007321622538100010001000542542542542542
2004541504325300010002000200018000052254154124832742000200020005415411110011000007321622538100010001000542542542542542
20045414017025300010002000200018000052254154124832742000200020005415411110011000007321622538100010001000542542542542542
2004541408525300010002000200018000152254154124832742000200020005415411110011000007321612538100010001000542542542542542
2004541404348300010002000200018000052254154124832742000200020005415411110011000007321622538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007321622538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000037321622538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007321622538100010001000542542542542542

Test 2: Latency 1->2 roundtrip

Code:

  fcvtzs w0, s0
  fmov d0, x0
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 13.0038

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f203a3f4f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2cfd0d5map dispatch bubble (d6)dbddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30204130038974000000001300231194172540100101192000010000100200001000050062149791480103401300131300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000001310121602212954210000100001000010100130039130039130384130039130039
30204130038974000000001300231194172540100101002000010000100200001000050062149791480103401300131300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000001310121602212952510000100001000010100130039130039130377130048130039
30204130038974000012352001300231194172540100101002000010000100200001000050062151231480194501300131300381300381254763126249301002001000020000200100002000013003813004111202011009910010100100001000010000000001310121602312952510000100001000010100130039130039130039130039130039
30204130038974000000001300231194172540100101002000010000100200001000050062149791480103401300131300381300381256073126246301002001000020000200100002000013003813003811202011009910010100100001000010000000001310121602212952510000100001000010100130039130042130039130039130039
302041300389740000000013002311941810740100101002000010000100200001000050062149791480103401300131300381300381254763126249301002001000020000200100002000013003813004351202011009910010100100001000010000040021384121602212952510003100001000010100130039130039130039130039130039
3020413003897400006360001300231194174640100101002000010000100200001000050062150271480114601300131300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001004010000000001310121602212952510000100001000010100130039130039130039130039130039
30204130038974000000001300231194172540100101002000010000105200001000050062149791480103401300131300381300381254763126250301002001000020000200100002000013003813003811202011009910010100100001000010000000321310121602212952710000100001000010100130041130040130039130039130039
302041300389740010120011300251194172540148101032000310005101206941000050062149791480103401302931300391300381256193126246301002001000020000200100002000013003813003811202011009910010100100001000210000010001310151602212952910000100001000010100130039130039130040130198130039
302041300411008000000001300231194172540100101002000010000100200001000050062149791480103401300131300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001000010000000001310121702212952510000100001000010100130042130379130039130039130039
3020413003897400000000130023119417110401001010020000100001002000010000500622426514801034013001313003813003812547625126248301002001000020000200100002000013037913003811202011009910010100100001000010000010301310121603412981610000100001000010100130040130049130071130049130043

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0038

retire uop (01)cycle (02)03mmu table walk data (08)09l2 tlb miss data (0b)18191e1f3a3f4f51schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)60696b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)l1d cache writeback (a8)acbranch mispred nonspec (cb)cfd0d5map dispatch bubble (d6)d9ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30024130038974000000001300241194172540010100102000010000102000010000506214979148000250130013013003813003812552131262683001020100002000020100002000013003813003811200211091010010100001000100000001270021601112952510000100001000010010130039130039130039130039130039
30024130038974000000001300231194172540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001000100000001270011601112952510000100001000010010130039130039130039130039130039
300241300389740000024001300231194182540010100102000010000102000010000506214979148000250130062013003813003812549831262683018020100002000020100002000013003813003811200211091010010100001000100002001270011601112952510000100001000010010130039130039130039130039130039
30024130038974000000001300231194192540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001000100000001270041601112959910000100001000010010130039130439130309130039130039
300241300389750000112001300231194172540010100102000010000102000010000506214979148000250130013013003813003912549831262703001020100002000020100002000013003813003811200211091010010100001000100000001270011601112952510000100001000010010130039130039130039130039130039
30024130038974000000001300231194172540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001000100000001270011601112952510000100001000010010130039130039130039130039130039
30024130038974000000001300231194172540010100102000010000102000010000556217283148000250130013013003813003812550131262683001020100002000020100002000013003813003811200211091010010100001000100000001270011601112952510000100001000010010130039130039130039130085130039
30024130039974000000001300231194172540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001000100000001270011601112952510000100001000010010130039130039130039130039130039
30024130038974000000001300251194172540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001000100000001270011601112952510000100001000010010130039130040130039130075130040
30024130038974000000001300231194172540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002013213003813003811200211091010010100001020100001001270011601112952510000100001000010010130039130039130039130039130039

Test 3: throughput

Count: 8

Code:

  fcvtzs w0, s8
  fcvtzs w1, s8
  fcvtzs w2, s8
  fcvtzs w3, s8
  fcvtzs w4, s8
  fcvtzs w5, s8
  fcvtzs w6, s8
  fcvtzs w7, s8
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5006

retire uop (01)cycle (02)03mmu table walk data (08)18191e1f3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)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)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)ec? simd retires (ee)? int retires (ef)f5f6f7f8fd
16020440064310000600322524010480100160004100160020500144013204002240041400411997761999216012020016003220016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002240041400411997761999216012020016022420016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042
16020440041300000006972524010480100160004100160020500144013204002240041400411997761999216012020016003220016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002240041400411997761999216012020016003220016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042
16020440041300000003225240104801001600041001600205001440132040212400414004119977371999216012020016003220016003240041400411180201100991008010010000191115117116114003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002240041400411997761999216012020016003220016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042
1602044004131000000322524010480100160004100160020500144013214002240041400411997761999216012020016003220016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042
1602044004129900000322524010480100160004100160020500144013204002240041400411997761999216012020016003220016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002240041400411997761999216012020016003220016024040064400521180201100991008010010000001115117116114003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002240041400411997761999216012020016003220016003240041400411180201100991008010010000001115117116114003880000080000801004004240042400424004240042

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5005

retire uop (01)cycle (02)03mmu table walk data (08)1e3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)5f60696b6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fld unit uop (a6)l1d cache writeback (a8)accdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)ea? simd retires (ee)? int retires (ef)f5f6f7f8fd
1600244005530000422524001080010160000101600005014400000040022040041400411999632002116001020160000201600004004140041118002110910800101000005020616244003880000080000800104004240042400424004240042
1600244004130000422524001080010160000101600005014400000040022040041400411999632002116001020160000201600004004140041118002110910800101000005020416444003880000080000800104004240042400424004240042
1600244004130000422524001080010160000101600005014400000040022040041400411999632002116001020160000201600004004140041118002110910800101000005020616244003880000080000800104004240042400424004240042
16002440041299007072524001080010160000101600005014400000040022040041400411999632002116001020160000201600004004140041118002110910800101000005020416244003880000080000800104004240042400424004240042
160024400412990342252400108001016000010160000501440000004002204004140041199963200211600102016000020160000400414004111800211091080010100021005020416444003880000080000800104004240042400424004240042
160024400413000042252400108001016000010160000501440000004002204004140041199963200211600102016000020160000400414004111800211091080010100020405020616924003880000080000800104004240042400424004240042
160024400413000063252400108001016000010160000501440000004002204004140041199963200211600102016000020160000400414004111800211091080010100020405020216424003880000080000800104004240042400424004240042
160024400413000042252400108001016000010160000501440000014002204004140041199963200211600102016000020160000400414004111800211091080010100014415020416244003880000080000800104012340042400424004240042
160024400412990042252400108001016000010160000501440000004002204004140041199963200211600102016000020160000400414004111800211091080010100019505046416244003880000080000800104004240042400424004240042
16002440041299004225240010800101600001016000050144000000400220400414004119996320021160010201600002016000040041400411180021109108001010007205020416424003880000080000800104004240042400424004240042