Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMU (vector, 4S)

Test 1: uops

Code:

  fcvtmu v0.4s, v0.4s
  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
10043037230126125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003022303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110001073116112701100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303721100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtmu v0.4s, v0.4s
  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)03071e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372331061295472510100100100001001000062642771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003723300346295472510100100100001001000050042771600300183003730037282643287451012520010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830226
102043003723312161295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001001371011611296330100001003003830038300383003830038
102043003723300612954725101001001000010010000626427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010003710116112963325100001003003830038300383003830038
102043003723210103295472510100100100001001000062642771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000671011711296330100001003003830038300383003830038
10204300372320061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000671011611296330100001003003830038300383003830038
1020430037233007262954725101001001000012510000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000710216122963325100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000371011611296330100001003003830038300383003830038
102043003723300612954725101251001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010007571011611296330100001003003830038300383003830038
10204300372330061295472510100100100001001000062642771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000371011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a1e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372320000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001010640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372320001061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330001061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330001061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372320001061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330001061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtmu v0.4s, v8.4s
  fcvtmu v1.4s, v8.4s
  fcvtmu v2.4s, v8.4s
  fcvtmu v3.4s, v8.4s
  fcvtmu v4.4s, v8.4s
  fcvtmu v5.4s, v8.4s
  fcvtmu v6.4s, v8.4s
  fcvtmu v7.4s, v8.4s
  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)03080b18191e1f3a3f51inst 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)9fa6a8acc2c5branch mispredict (cb)cdcfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060155000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100040011151180001600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100006011151180001600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100013011151180001600200360800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000350011151180001600200360800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000190011151180001600200360800001002004020040200402004020040
8020420039156000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100003011151180001600200360800001002004020040200402004020040
80204200391550000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000363011151180001600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180001600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180001600200360800001002004020040200402004020040
8020420039156000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100003011151180001600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b181e3f51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020616262003680000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100035020616632003680000102004020040200402004020040
8002420039155000040258001010800001080000506400001201412003920039999631001980010208000020800002003920039118002110910108000010001265020216362003680000102004020040200402004020040
80024200391550009402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020216222003680000102004020040200402004020040
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100435020216222003680000102004020040200402004020040
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100405020216622003680000102004020040200402004020040
80024200391550003822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100205020216222003680000102004020040200402004020040
80024200391560000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100405020216232003680000102004020040200402004020040
800242003915500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001004505020516222003680000102004020040200402004020040
800242003915500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001005995020316632003680000102004020040200402004020040