Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZS (vector, integer, 8H)

Test 1: uops

Code:

  fcvtzs v0.8h, v0.8h
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)030818191e3f4e51inst issue (52)~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 neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000010325472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723000026525472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000073134112629100030383038303830383038
100430372400008225472510001000100039816013018303730372414328951000100010003037303711100110000095116112629100030383038308630383086
10043084240111418225472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372300006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs v0.8h, v0.8h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030a1e1f3a3f4e51inst 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)inst neon or fp (9a)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000170295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372240000168295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372240000336295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372240000166295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830080300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730326282643287451010020010000200100003003730037111020110099100100100001000000371021622296330100001003003830038300383003830038
1020430037225008803729295472510100100100001001000050042785120300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003722503000146129421271102661511009615512100793429465913052230604306082831364290181210924212183250123223061230698161102011009910010010000100006027371021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)inst neon or fp (9a)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100253003722402202954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640316222962910000103003830038300383003830038
1002430037225267612954725100101010000101000050427716003001830037300372828672876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225438612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722501052953825100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225061295382510010101000010100005042771601300183003730037282863287671001020100002010000300853008411100211091010100001005530640216222962910000103003830038300383003830038
1002430037224187152954725100101010000101000050427716013001830037300842828632876710010201000020100003003730037111002110910101000010000640224222962910000103003830038300383003830038
100243003722545612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010200640216222962910000103003830038300383003830038
1002430037225630612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225204612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037224306612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs v0.8h, v8.8h
  fcvtzs v1.8h, v8.8h
  fcvtzs v2.8h, v8.8h
  fcvtzs v3.8h, v8.8h
  fcvtzs v4.8h, v8.8h
  fcvtzs v5.8h, v8.8h
  fcvtzs v6.8h, v8.8h
  fcvtzs v7.8h, v8.8h
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03070a1e3f51inst 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)696d6edispatch stall (70)72scheduler 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)inst neon or fp (9a)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150110302580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151183164420036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151184164420036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151185165520036800001002004020040200402004020040
8020420039150110512580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151183164420036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151185165520036800001002004020040200402004020040
8020420039150110952580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151185165420036800001002004020040200402004020040
8020420039156110302580108100800081008002050064013220020200392003999770699908012020080144200800322003920039118020110099100100800001000011151183165320036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151184164420036800001002004020040200402004020040
80204200391501106002580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000311151184165420036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013220020200392003999770699908012020080032200800322003920039118020110099100100800001000011151185166520036800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e3f51inst 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)5f60696d6edispatch 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)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391560243625800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050207166172003680000102004020040200402004020040
8002420039156040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502018166162008780000102004020040200402004020040
800242003915502842580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010105020171617172003680000102004020040200402004020040
80024200391560618258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000502014161762003680000102004020040200402004020040
80024200391560682580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020171617172003680000102004020040200402004020040
8002420039156040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000502081617122003680000102004020040200402004020040
80024200391550409258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000502017166172003680000102004020040200402004020040
80024200391560259258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000502017161782003680000102004020040200402004020040
800242003915504025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050206166172003680000102004020040200402004020040
8002420039155082258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000502081617172003680000102004020040200402004020040