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, fixed-point, D to W)

Test 1: uops

Code:

  fcvtzs w0, d0, #3
  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
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541504325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000107311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542
2004541404325300010002000200018000052254154124832742000200020005415411110011000007311611538100010001000542542542542542

Test 2: Latency 1->2 roundtrip

Code:

  fcvtzs w0, d0, #3
  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)03l2 tlb miss data (0b)1e1f3f4f51schedule 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)l1d cache writeback (a8)acc2branch cond mispred nonspec (c5)cdcfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
30204130038100803013002611941725401001010020000100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001001000000000131012162212952510000100001000010100130039130039130156130040130039
30204130038100800013002311941725401001010020000100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001001000000000131012162212952510000100001000010100130039130039130039130039130039
30204130038100800013002311941725401001010020000100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001001000000000131011162212952510000100001000010100130039130039130039130039130039
30204130074100809013002311942125401001010020000100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001001000000000131012163212952510000100001000010100130039130039130039130039130039
30204130038100800013002311941725401001010020000100001002000010000500621497914801034013001301300381300381254763126246302672001000020000200100002000013003813003811202011009910010100100001001000000000131012162212952510000100001000010100130039130039130039130039130039
302041300381008018013012811941725401001010020000100001002000010000500621497914816073013001401300391300381254763126246301002001000020000200100002000013003813003811202011009910010100100001001000000000131012162212952510000100001000010100130039130039130039130039130039
30204130038974117721613002311941725401001010020000100001002000010000500621502714801258013001301300381300381254763126246301002001000020000200100002000013003813003811202011009910010100100001001000010000138312162212952810000100001000010100130039130039130039130039130039
3020413003897400013002311941725401001010020000100001002000010000500621497914801034113001301300381300381254773126246301002001000020000200100002000013003813003811202011009910010100100001001000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400013002311941725401001010020000100001002000010000500621497914801034113001301300381300381254763126246301002001000020000200100002012913003813003811202011009910010100100001001000003000131012162212952510000100001000010100130039130039130039130039130073
3020413003897400013002311942725401001010020004100001002000010000500621497914801034013001301300381300381254763126246301002001000020000200100002000013003813003811202021009910010100100001001000000000131012162212952510000100001000010100130039130039130039130039130039

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)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)ld unit uop (a6)l1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)f5f6f7f8fd
3002413003897400005400130023119417254001010010200001000010201161000050621497914800025113001301300381300381255373126268300102010000200002010000204811300391300381120021109101001010000100100001030012702161112952510000100001000010010130039130039130039130039130039
300241300389740000000130023119417254001010010200001000010200001000050621497914800025113001301300381300381254983126303300102010000200002010000200001300381300381120021109101001010000100100000000012704162312952510000100001000010010130039130039130039130039130039
3002413003997400001200130023119417254001010010200001000010200001000050621497914800025113001301300381300381254983126313300102010000200002010000200001300381300381120021109101001010000100100000000012704161112952510000100001000010010130039130039130039130044130039
3002413003897600000001300231194182540010100172000010000102000010000506214979148000250130013013004013003812549828126274300102010000200002010000200001300421301221120021109101001010000100100004000012701161112952510000100001000010010130039130039130039130039130039
3002413003897400000001300261194171094001010010200001000010200001000050622470314800025113001301300381300381254983126268300102010000200002010000200001300381300405120021109101001010000100100000000012701161112952510000100001000010010130373130039130039130039130374
300241300389740000000130023119418254001010010200001000010200001000050621497914800025113023301300381300381254983126268300102210000200002010000200001300381300381120021109101001010000100100100000012701161112979810000100001000010010130039130039130039130039130039
30024130038974000094500130023119417254001010010200001000010200001000050621507514800025113001301300381300381254983126271300102010000200002010000200001300381300381120021109101001010000104100000030012701161112952510000100001000010010130039130039130039130040130039
300241300389740000300130023119417254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100004000012701161112952510000100001000010010130039130041130039130039130039
300241300389770000102900130025119417254003410010200001000010200001000050621507514811133113001301300381300381254983126268300102010000200002010000204901300381300381120021109101001010000100100002000012701162112952510000100001000010010130039130039130039130039130039
300241300389740000000130023119417254001010010200001000010200001000050621497914800025113001301300381300381254983126268300102010000200002010000200001300381300381120021109101001010000100100001000012701161112952510000100001000010010130039130039130039130043130039

Test 3: throughput

Count: 8

Code:

  fcvtzs w0, d8, #3
  fcvtzs w1, d8, #3
  fcvtzs w2, d8, #3
  fcvtzs w3, d8, #3
  fcvtzs w4, d8, #3
  fcvtzs w5, d8, #3
  fcvtzs w6, d8, #3
  fcvtzs w7, d8, #3
  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)03090f1e3f51schedule 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)9fst unit uop (a7)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
1602044006531000090825240104801001600041001600205001440132040022400414004119977619992160120200160032200160032400414004111802011009910080100100020111511711600400388000080000801004004240042400424004240042
1602044004131000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000280111511701600400388000080000801004004240042400424004240042
1602044004131000032252401048010016000410016002050014401321400224004140041199776199921601202001600322001600324004140041118020110099100801001000620111511701600400388000080000801004004240042400424004240042
160204400413100003225240104801001600041001600205001440132140022400414004119977619992160120200160032200160032400414004111802011009910080100100023111511701600401058000080000801004004240042400424004240042
160204400413100003225240104801001600041001600205001440132040022400414004119977619992160120200160032200160032400414004111802011009910080100100030111511701600400388000080000801004004240042400424004240042
1602044004131000069725240104801001600041001600205001440132040022400414004119977619992160120200160032200160032400414004111802011009910080100100010111511701600400388000080000801004004240042400424004240042
1602044004131000032252401048010016000410016002050014401321400224004140041199776199921601202001600322001600324004140041118020110099100801001000280111511701600400388000080000801004004240042400424004240042
160204400413100003225240104801001600041001600205001440132040022400414004119977619992160120200160032200160032400414004111802011009910080100100006111511701600400388000080000801004004240042400424004240042
160204400413100003225240104801001600041001600205001440132140022400414004119977619992160120200160032200160032400414004111802011009910080100100026111511701600400388000080000801004004240042400424004240042
160204400413100003225240104801001600041001600205001440132040022400414004119977619992160120200160032200160032400414004111802011009910080100100020111511701600400388000080000801004004240042400424004240042

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)18191e1f3a3f51schedule 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)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 access (a0)ld unit uop (a6)l1d cache writeback (a8)a9accfd0d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)eaec? simd retires (ee)? int retires (ef)f5f6f7f8fd
1600244005531000000084252400108001016000010160000501440000040022400414004119996032002116001020160000201600004004140041118002110910800101000000502001161140038800000080000800104004240042400424004240042
1600244004131100000042252400108001016000010160000501440000040022400414004119996032002116001020160000201600004004140041118002110910800101000000502001161140038800000080000800104004240042400424004240042
16002440041310000000707252400108001016000010160000501440000040022400414004119996032002116001020160000201600004004140041118002110910800101000000502001161140038800000080000800104004240042400424004240042
160024400413100040004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000246502001161140038800000080000800104004240042400424004240042
1600244004131000000042252400108001016000010160000501440000040022400414004119996032002116001020160000201600004004140041118002110910800101000100502001161140038800000080000800104004240042400424004240042
1600244004131000000042252400108001016000010160000501440000140022400414004119996032002116001020160000201600004004140041118002110910800101000000502001161140038800000080000800104004240042400424004240042
1600244004131100000042252400108001016000010160000501440000040022400414004119996032002116001020160000201600004004140041118002110910800101000000502001161140038800000080000800104004240042400424004240042
16002440041310000132004225240010800101600001016000050144000014002240041400411999603200211600102016000020160000400414004111800211091080010100000237502001161140038800000080000800104004240042400424004240042
160024400413100000006225240010800101600001016000050144000014002240041400411999603200211600102016000020160000400414004111800211091080010100000222502001161140038800000080000800104004240042400424004240042
1600244004131000051004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000207502001161140038800000080000800104004240042400424004240042