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

FCVTZU (scalar, integer, S to X)

Test 1: uops

Code:

  fcvtzu x0, 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)03mmu table walk instruction (07)mmu table walk data (08)l2 tlb miss instruction (0a)l2 tlb miss data (0b)191e1f3a3f51schedule 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 tlb access (a0)l1d tlb miss (a1)st unit uop (a7)l1d cache writeback (a8)a9acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
2004541400000000432530001000200020001800015225415412483274200020002000541541111001100000000007321622538100010001000542542542542542
2004541400000000432530001000200020001800015225415412483274200020002000541541111001100000000007321622538100010001000542542542542542
2004541400000000432530001000200020001800015225415412483274200020002000541541111001100000000007321622538100010001000542542542542542
2004541400000000432530001000200020001800015225415412483274200020002000541541111001100000000007321622538100010001000542542542542542
200454140000000043253000100020002000180001522541541248327420002000200054154111100110000200041007321622538109910001000542542542542542
2004541400000000138253000109620002000180001522541541273732022082000200054154111100110000200236808821622538100010001000542542617617542
200454150000001801862530001000200020001800015225416202483274220820002000541541111001100020010307321622538100010001000542542542542649
2004623500000000652530001000200020001800015885415412481127420002000200054162321100110000001022007321622538100010001000542625618620623
200462350000008801922530001000200020001800015225415412483274200020002000541541111001100000000007321623538100010001000542542621542542
20045414010003881642532861000200020001800015785415412723320200020002000541541111001100000010007321632538100010001000542624542623624

Test 2: Latency 1->2 roundtrip

Code:

  fcvtzu x0, 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)03l1i tlb fill (04)mmu table walk data (08)l2 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)696d6emap 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 miss (a1)ld unit uop (a6)l1d cache writeback (a8)acc2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30204130038974000000021300231194202540100101002000010000100200001000050062149791480103413001313003813003812547631262463010020010000200002001000020000130071130040112020110099100101001000010001000000000013144176912953110000100001000010100130039130039130039130039130039
30204130038974000000021300231194172540100101002000010000100200001000050062149791480103413001313003813003812547631262463010020010000200002001000020000130056130043112020110099100101001000010001000000000013146165612952510000100001000010100130039130039130039130039130039
302041300389740000030213002311941725401001010020000100001002000010000500621497914801034130013130038130038125476312624630100200100002000020010000200001300831300501120201100991001010010000100010000051000013144165612952510000100001000010100130039130039130039130039130039
30204130038973000000021300231194172540100101002000010000100200001000050062149791480103413001313003813003812547631262463010020010000200002001000020000130085130056112020110099100101001000010001000000000013149167912953010000100001000010100130039130039130039130039130083
30204130038974000000021300231194172540100101002000010000100200001000050062149791480103413001313003813003812547631262463010020010000200002001000020000130042130038112020110099100101001000010001000000000013148168812952510000100001000010100130039130039130039130039130039
30204130038974000000021300231194172540100101002000010000100200001000050062149791480103413001313003813003812547631262463010020010000200002001000020000130093130044112020110099100101001000010001000000000013148167812952510000100001000010100130039130039130039130039130039
30204130038974000000021300231194152540100101002000010000100200001000050062149791480103413001413003813003812547631262463010020010000200002001000020000130099130051112020110099100101001000010001000000000013148168812952510000100001000010100130039130039130039130039130039
30204130038974000000021300231194172540100101002000010000100200001000050062149791480103413001313003813003812547631262463010020010000200002001000020000130080130044112020110099100101001000010001000000000013148167912952510000100001000010100130039130039130039130039130039
30204130038974000000021300231194172540100101002000010000100200001000050062149791480103413001313003813003812550731262463010020010000200002001000020000130038130038112020110099100101001000010001000000000013148167812960110000100001000010100130039130039130039130039130039
30204130038974000000021300231194172540100101002000010000116200001000050062170431480252413001313003813008212548031262463010020010000200002001000020000130038130038112020110099100101001000010001000000000013148167412952510000100001000010100130039130039130039130039130039

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0038

retire uop (01)cycle (02)03mmu table walk data (08)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)9fld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
300241300389730000001300261194172540010100102000010000102000010000506214979148000251130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001010000000000112702161112952510000100001000010010130039130039130039130039130039
300241300389740000001300231194242540010100102000010000102000010000506214979148000251130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112952510000100001000010010130041130039130039130039130039
3002413003897400060013002311941725400101001020000100001020000100005062149791480002501300130130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010100000120000012701161112952510000100001000010010130039130039130069130043130039
300241300389740000001300231194242540010100102000010000102000010000506215445148000250130013013003913003812549831262683001020100002000020100002000013003813003921200211091010010100001010000000000012701161112952510000100001000010010130039130039130040130039130039
300251300389740000001300231194172540010100102000010000102000010000506214979148000250130013013003813003812551231262683001020100002000020100002000013003813003811200211091010010100001010000000000012702162112952510000100001000010010130039130039130039130039130039
300241300389740000001300251194172540010100102000010000102000010000556214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112952510000100001000010010130039130039130039130039130039
300241300389740000001300241194172540010100102000010000102000010000506214979148000250130017013003913003912549831262773001020100002000020100002000013003813003811200211091010010100001010000000000012701161112952510000100001000010010130039130039130039130039130039
300241300389730000001300271194172540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112952510000100001000010010130039130039130039130039130039
300241300389740006001300231194172540010100102000010000102000010000506214979148000250130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112952510000100001000010010130039130039130069130047130039
300241300389740000001300271194172540010100102000010000102000010000506214979148000251130013013003813003812549831262683001020100002000020100002000013003813003811200211091010010100001010000000000012701161112952510000100001000010010130039130039130039130039130045

Test 3: throughput

Count: 8

Code:

  fcvtzu x0, s8
  fcvtzu x1, s8
  fcvtzu x2, s8
  fcvtzu x3, s8
  fcvtzu x4, s8
  fcvtzu x5, s8
  fcvtzu x6, s8
  fcvtzu x7, s8
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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)60696b6d6emap stall dispatch (70)rob full (74)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 miss (a1)ld unit uop (a6)l1d cache writeback (a8)acc2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)ea? simd retires (ee)? int retires (ef)f5f6f7f8fd
1602044006630000000322524010480100160004100160020500144013204002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117116104003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016004003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016214010380000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013214002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016004003880000080000801004004240042400424004240042
1602044004129900000322524010480100160004100160020500144013214002204004140041199775619992160120200160032200160032400414004111802011009910080100100000001115117016104003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016004003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016004003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013214002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016104003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016004003880000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002204004140041199770619992160120200160032200160032400414004111802011009910080100100000001115117016004003880000080000801004004240042400424004240042

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)031e3f51schedule 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)5f60696d6emap 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)l1d tlb miss (a1)ld unit uop (a6)a9accfd0d5map dispatch bubble (d6)daddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
1600244005430004225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010102200050200316011400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000050205116011400388000080000800104004240042400424004240042
1600244004129904225240010800101600001016000050144000001400224004140041199963200211600102016000020160000400414004121800211091080010100000050200116221400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000050200116011400388000080000800104004240042400424004240042
1600244004129904225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000050200116011400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000001400224004140041199963200211600102016000020160000400414004111800211091080010100000050200116011400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000001400224004140041199963200211600102016000020160000400414004111800211091080010100000050200116011400388000080000800104004240042400424004240042
1600244004131004225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000050200116011400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100000050200116011400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000000400224004140041199963200211600102016000020160000400414004111800211091080010100002050200116011400388000080000800104004240042400424004240042