Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (scalar, integer, S from S)

Test 1: uops

Code:

  ucvtf s0, s0
  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)03181e3f4e51inst 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
10043037240126125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230061254725100010001000398160130183037303724143289510001000100030373037111001100038073116112629100030383038303830383038
10043037240018725472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724106125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf s0, s0
  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)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)60696b6d6edispatch 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)9fa0a8accfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233061295472510100100100001001000050042771601300180300373003728271628740101002001000820010000300373003711102011009910010010000100000710116015296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372320117295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383007730038
10204300372320103295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300863003830132
1020430037242061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116041296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
1020430037233084295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
10204300372320346295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000710116011296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e1f3a3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000010329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640516122962910000103003830038300383003830038
1002430037232000006629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037233000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001001200640216222962910000103003830038300383003830038
10024300372251000014529547251001010100001010000504277160030018300853003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250000014529547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250000021429547251001010100001010000504277160130018300373003728286328805100102010000201000030133300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf s0, s8
  ucvtf s1, s8
  ucvtf s2, s8
  ucvtf s3, s8
  ucvtf s4, s8
  ucvtf s5, s8
  ucvtf s6, s8
  ucvtf s7, s8
  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)03191e3f51inst 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)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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000311151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010001011151181160020036800001002004020040200402004020049
8020420048156012642680116100800161008002850064019620029200482004899769998680128200800382008003820049200491180201100991001008000010000022251281231120045800001002005020050200492004920049
80204200481550063426801161008001610080028500640196201522004920048997610998680128200800382008003820048200481180201100991001008000010001022251281231120045800001002004920049200992005020049
802042004815500922780116100800161008002850064019620029200482004899769998680128200800382008003820048200481180201100991001008000010000022251281231120045800001002004920049200492004920049
8020420048155006426801161008001610080028500640196200292004820048997610998680128200800382008003820048200481180201100991001008000010000022251281232120045800001002004920050200492004920049
802042004816100302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010001011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000611151180160020036800001002004020040200402009420040
802042003915500302580108100800081008002050064013220020200392003999776999080120200802352008003220039200391180201100991001008000010001011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e3f51inst 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)9fa6a8abaccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020216112003680000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001005020216112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000035020116112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020216112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020216222003680000102004020040200402004020040
8002420039156000168258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050201260112003680000102004020040200402004020040
8002420039155002224025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020216212003680000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020216112003680000102004020040200402004020040