Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FCVTNS (scalar, D to W)

Test 1: uops

Code:

  fcvtns w0, d0
  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 (01)cycle (02)03081e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst integer (97)a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
2004541400432530001000200020001800005225415412483274200020002000541541111001100010007311611538100010001000542542542542542
2004541400432530001000200020001800005225415412483274200020002000541541111001100000007311611538100010001000542542542542542
2004541400432530001000200020001800005225415412483274200020002000541541111001100000007311611538100010001000542542542542542
2004541400432530001000200020001800015225415412483274200020002000541541111001100000007311611538100010001000542542542542542
20045414012432530001000200020001800005225415412483274200020002000541541111001100000307311611538100010001000542542542542542
2004541400432530001000200020001800005225415412483274200020002000541541111001100004307311611538100010001000542542542542542
20045415101384830001000200020001800005225415412483274200020002000541541111001100000347311611538100010001000542542542542542
2004541400432530001000200020001800005225415412483274200020002000541541111001100000007311611538100010001000542542542542542
2004541400432530001000200020001800005225415412483274200020002000541541111001100000007311611538100010001000542542542542542
2004541400852530001000200020001800015225415412483274200020002000541541111001100000007311611538100010001000542542542542542

Test 2: Latency 1->2 roundtrip

Code:

  fcvtns w0, d0
  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 (01)cycle (02)03070818191e1f3a3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)6061696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)ld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
3020413003897400000001300231194172540100101002000010000100200001000050062149791480103402130013013003813003812547631262463010020010000200002001000020000130038130078512020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400000001300231194172540100101002000010000100200001000050062149791480103400130013013003813007412547631262463010020010000200002001000020000130097130057112020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400000001300241194172540100101002000010000100200001000050062149791480103400130013013003813003812547631262463010020010000200002001000020000130038130104112020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400000001300241194172540100101002000010000100200001000050062149791480103400130013013003813003812547631262463028420010000200002001000020000130038130092112020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400000001300231194172540100101002000010001100200001000050062149791480103405130013313003813003812547631262463010020010000200002001006420000130038130086112020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400000001300231194172540100101002000010000100200001000050062149791480103400130013013003813003812547631262463010020010000200002001000020000130038130081512020110099100101001000010000100000000001131012162212952510000100001000010100130039130039130039130039130039
3020413003897400003001300231194172540100101002000010000100200001000050062149791480103400130013013003813003812547631262463010020010000200002001000020000130038130038112020110099100101001000010000100000000010131012162212952510000100001000010100130039130039130039130039130039
30204130038974000000013002311941725401001010020000100001002000010000500621497914801034001300130130038130038125476201262533010020010000200002001000020000130038130091112020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130074
3020413003997400000001300231194082540100101002000010000100200001000050062149791480103400130013013003813003812547631262463010020010000200002001000020000130038130104112020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130039
3020413003897400000001300231194202540100101032000010000100200001000050062149791480103400130013013003813003812547631262463010020010000200002001000020000130038130038112020110099100101001000010000100000000000131012162212952510000100001000010100130039130039130039130039130039

1000 unrolls and 10 iterations

Result (median cycles for code): 13.0038

retire (01)cycle (02)0307080a0b18191e1f3a3f4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ecld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
300241300399740000000001300231194172540010100102000010000102000010000506214979148000250130013130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010001000000000127021622129525100000100001000010010130091130064130039130039130039
300241300389740000000001300231194172540010100102000010000102000010000506214979148000250130013130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010001000000000127021622129525100000100001000010010130042130058130039130046130039
30024130038974000000000130023119421254001010010200001000010200001000050621497914800025013001313003813003812549831262683001020100002000020100002000013003813003811200211091010010100001000100880220004500185142724813119010004137100001000010010130044130039130050130039130046
300241300389740000000001300231194172540010100102000010000132046610000506214979148000251130013130359130038125498312648130010201000020476201000020000130038130038112002110910100101000010001000000000127021622129525100000100001000010010130372130068130039130042130039
300241300389740000000011300231194172540010100102000010000102000010000506214979148000250130013130038130038125498312626830010201000020000221000020000130038130038112002110910100101000010201000000900127025022129528100000100001000010010130040130039130040130043130039
300241300399760000000001300231194172540010100102000010000102000010000506214979148204450130013130038130038125498312626830010201000020000201000020000130038130038112002110910100101000010001000000000127021622129525100000100001000010010130068130047130039130039130039
300241300389740000000001300231194172540010100102000010000102000010000506214979148000250130013130038130038125498312626830010201000020000201000020482130038130038112002110910100101000010001000010000127021622129525100050100001000010010130053130039130039130039130039
300241300389740000001235201300231195542540010100102000010000102000010000506214979148000250130013130038130038125498312626830010221000020000201000020000130038130038112002110910100101000010001000000000127021632129528100000100001000010010130060130040130039130039130039
3002413003997400004000013002311941725400101001020000100001020466100005062149791480002501300131300381300381254993126268300102010000200002010000200001300381303741120021109101001010000100010000001714700127021622129525100000100001000010010130041130383130039130064130039
300241300389740100000001300231194182540010100102000010000102000010098506214979148000250130015130038130038125498912626830010201000020000201000020000130038130038112002110910100101000010201000000900127025022129525100000100001000010010130468130043130039130044130039

Test 3: throughput

Count: 8

Code:

  fcvtns w0, d8
  fcvtns w1, d8
  fcvtns w2, d8
  fcvtns w3, d8
  fcvtns w4, d8
  fcvtns w5, d8
  fcvtns w6, d8
  fcvtns w7, d8
  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440041299000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000000111511701600400388000080000801004004240042400424004240042
16020440041300000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000000111511701600400388000080000801004004240042400424004240042
16020440041300000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000000111511701600400388000080000801004004240042400424004240042
16020440041299000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000000111511701600400388000080000801004004240042400424004240042
1602044020731400000008022524010480100160004100160020500144013204002240041400411997714199921601202001600322001600324004140041118020110099100801001000000000111511701600400388000080000801004004240042400424004240042
16020440041300000000074252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000000111511711600400388000080000801004004240042400424004240042
160204400413000000000259252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000001000111511701600400388000080000801004004240042400424004240042
160204400413000000012074252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000030111511701600400388018880000801004004240042400424004240201
16020440041300001000032252403788010016040010016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000000111511701600400388000080000801004004240042400424004240042
16020440041310000000032252401048010016000410016002050014401320400224004140041199776199921601202001600322001600324004140041118020110099100801001000000030111511701600400388000080000801004004240042400424004240042

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)74scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)9fa6a8acc2cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024410673092110000182818724173281062161358101614285014525440407194067340681202100582042716143420162228201617844076241220718002110910800101020123540530304205284094881399080000800104028440198400424004241401
1600244101031900022276010125725240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000050200216114003880000080000800104004240042400424004240042
1600244004129900000004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000050200216114003880000080000800104004240042400424004240042
1600244004129900000004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000050200116124003880000080000800104004240042400424004240042
1600244004130000000004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000050200116114003880000080000800104004240042400424004240042
16002440041300000000042252400108001016000010160000501440000040022400414004119996032002116001020160000201600004004140041118002110910800101000300502001161140038800001480000800104004240042400424004240042
1600244004130000000004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000050200116114003880000080000800104004240042400424004240042
1600254004130000000004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100100050200116114003880000080000800104004240042400424004240042
1600244004130000000004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000050200116114003880000080000800104004240042400424004240042
1600244004130000000004225240010800101600001016000050144000004002240041400411999603200211600102016000020160000400414004111800211091080010100000050200116134003880000080000800104004240042400424004240042