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 X)

Test 1: uops

Code:

  fcvtzs 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)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
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541505725300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
20045414052625300010002000200018000152254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000152254154124832742000200020005415411110011000007311611538100010001000542542542542542

Test 2: Latency 1->2 roundtrip

Code:

  fcvtzs 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)031e3f4f5051schedule 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)ld unit uop (a6)l1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)eb? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30204130038974393130025119417025401001010020000100001002000010000500621497914801034013001313003813003812547631262463010020010000200002001000020000130038130038112020110099100101001000010001000000300001310131633129525100000100001000010100130039130039130039130039130039
30204130038103793130023119417025401001010020000100001002000010000500621497914801034013001313003813003812547631262463010020010000200002001000020000130038130038112020110099100101001000010001000000000001310131633129525100000100001000010100130039130039130039130039130039
30204130038974918130023119417025401001010020000100001002000010000500621497914801034013001513003813003812547631262463010020010062200002001000020000130038130038112020110099100101001000010001000000000001310131633129525100000100001000010100130039130077130039130039130039
302041300389741194130023119417025401001010020000100001002000010000500621497914801034113001313003813003812547631262463010020010000200002001000020000130038130038112020110099100101001000010001000000000101310131633129525100000100001000010100130039130039130039130039130039
302041300389741068130023119417025401001010020000100001002000010000500621497914801034113001313003813003812547631262463010020010000200002001000020000130038130038112020110099100101001000010001000000000001310131633129525100000100001000010100130039130039130039130040130039
302041300389741152130023119417039401001010020000100001002000010000500621497914801988013001313003813003812547831262463010020010000200002001000020000130038130038112020110099100101001000010001000000600001310131633129613100000100001000010100130039130039130039130039130039
3020413003897445130023119417025401001010020000100001002000010000500621497914801034013001313003813003812547631262923010020010000200002001000020000130038130038112020110099100101001000010001000000000001310141633129525100000100001000010100130041130039130039130039130039
302041300389741098130023119417025401001010020000100001002000010000500621497914801034113001313003813003812547631262463010020010000200002001000020000130038130038212020110099100101001000010001000000300001310131633129525100000100001000010100130039130039130039130039130039
30204130038974834130023119417025401001010020000100001002000010000500621497914801034013001313003813007712548431262463010020010000200002001000020000130038130038112020110099100101001000010001000020000001310131633129525100000100001000010100130039130039130039130039130039
3020413003897327130023119417025401001010020000100001002012310000500621497914801034013001313003813003812547631262463010020010000200002001000020000130038130038112020110099100101001000010001000000000001310131623129525100000100001000010100130039130039130075130039130039

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0038

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)1e1f3f4f5051schedule 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 miss (a1)ld unit uop (a6)l1d cache writeback (a8)acc2branch cond mispred nonspec (c5)branch mispred nonspec (cb)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30024130038974000013002311941702540010100102000010000102000010000506214979148000251130013013003813003812549831262703001020100002000020100002000013003813003811200211091010010100001001000001200012706171112952510000100001000010010130039130039130039130039130039
3002413003897400001300231194170254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300431300381120021109101001010000100100000000012701161112952510000100001000010010130039130039130039130039130039
3002413003897400001300231194170254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100000000112701161112952510000100001000010010130039130039130039130039130039
3002513004297400001300231194170254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100000900012701161112952510003100001000010010130039130039130039130039130039
3002413036597400601300231194130254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000201262010000200001300381300382120022109101001010000100100000000012701161112952510000100001000010010130039130039130039130039130039
3002413003897400901300231194170254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100000000012702161112976210000100001000010010130039130039130042130039130039
3002413003897400001300231194170254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100003000012701161112952510000100001000010010130039130039130039130039130039
30024130038974000013002311941702540010100102000010000102000010000506214979148000251130013013003813003812549831262683001020100002000020100002013113008413004111200211091010010100001001000001500012701161112952710000100001000010010130039130039130039130039130039
3002413003897400001300231194170254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100000000012701161112952510000100001000010010130039130039130068130045130039
3002413004797400001300231194170254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100000300012701161112952510000100001000010010130039130039130039130039130039

Test 3: throughput

Count: 8

Code:

  fcvtzs x0, s8
  fcvtzs x1, s8
  fcvtzs x2, s8
  fcvtzs x3, s8
  fcvtzs x4, s8
  fcvtzs x5, s8
  fcvtzs x6, s8
  fcvtzs 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)03l2 tlb miss data (0b)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 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)? simd retires (ee)? int retires (ef)f5f6f7f8fd
160204400413000000053252401048010016000410016002050014401321400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511711600400388000080000801004004240042400424004240042
160204400413000000032252401048010016000410016002050014401321400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004004240042400424004240042
160204400413000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004004240042400424004240042
160204400413000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004004240042403644004240042
160204400413000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004004240042400424004240042
1602044004130000015032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004004240042400424004240042
1602044004130000000322524010480100160004100160020500144013204002240041400411997736199921601202001600322001600324004140041118020110099100801001000000111511701610400388000080000801004004240042400424004240042
160204400413000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004004240042400424004240042
160204400413000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004035940042400424004240042
160204400412990000032252401048010016000410016002050014401321400224004140041199776199921601202001600322001600324004140041118020110099100801001000000111511701600400388000080000801004004240042400424004240042

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)5f60696b6d6emap 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)st unit uop (a7)l1d cache writeback (a8)a9acc2cfd0d5map dispatch bubble (d6)dadbddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
16002440055300042252400108001016000010160000501440000004002204004140041199960320021160010201600002016000040041400411180021109108001010000000050200141610117400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000000400220400414004119996032002116001020160000201600004004140041118002110910800101000000005020091600512400388000080000800104004240042400424004240042
16002440041299042252402968001016000010160000501440000004021704004140041199960320021160010201600002016000040041400411180021109108001010000000050200131600611400388009080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000000400220400414004120024032002116001020160000201600004004140041118002110910800101000000005020091600116400388000080000800104004240042400424004240042
160024400413100422524001080010160000101600005014400000040022040041400411999603200211600102016000020160000400414004111800211091080010100000000502001016001112400388000080000800104004240042400424004240042
160024400413000422524001080010160000101600005014400000040022040041400411999603200211600102016000020160000400414012711800211091080010100000000502001216001112400388000080000800104004240042400424004240042
1600244004130007072524001080010160000101600005014400000040022040041400411999603200211600102016000020160000400414004111800211091080010100000000502001216001210400388000080000800104004240042400424004240042
160024400413000422524001080010160000101600005014400000040022040041400411999609200211600102016000020160000400414004111800211091080010100000000502001116001411400388000080000800104004240042400424004240042
16002440041299042252400108001016000010160000501440000004002204004140041199960320021160010201600002016000040041400411180021109108001010000000050200516001210400388000080000800104004240042400424004240042
1600244004130004225240010800101600001016000050144000000400220400414004119996032002116001020160000201600004004140041118002110910800101000000005020010160099400388000080000800104004240042400424004240042