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, 2D)

Test 1: uops

Code:

  fcvtmu v0.2d, v0.2d
  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)031e3f4e51inst 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
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110009373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724020725472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724010325472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100058073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtmu v0.2d, v0.2d
  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)030708090a0b18191e1f3f4e51inst 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)9fa0a1a8acc2cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233100000000196295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007100116212963325100001003003830038300383003830038
102043003723310000000014229547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
1020430037233000000000131229547251012510010000100100006264277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
102043003723300000000023329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372330000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100002000710011614296330100001003003830038300383003830038
10204300372330000000006129547251010010010000100100005004277160030018300373003728264328744101002001000020010000300373003711102011009910010010000100000000710011621296330100001003003830038300383003830038
102043003723200000000061295472510125125100001251000066442771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000004800710011611296330100001003003830038300383003830038
10204300372330000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373022711102011009910010010000100001000710011611296330100001003003830038300383003830038
10204300372321001000513526129547251010010010032100100005004277160030018300373003728275328745101002001000020010000300373003711102011009910010010000100000000710011611296330100001003003830038300383003830038
10204300372320000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710021611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e3f4e51inst 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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037232000010722954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
100243003723300008902954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
1002430037232000012132954725100101010000101000050427716003001830037300372828672876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372330000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372330000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
1002430037233000516129547251001810100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000186403163329629010000103003830038300383003830085
10024300372330000612954725100101010000101000055427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403164329629010000103003830038300383003830038
100243003724100001622954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403243329629010000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000126403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtmu v0.2d, v8.2d
  fcvtmu v1.2d, v8.2d
  fcvtmu v2.2d, v8.2d
  fcvtmu v3.2d, v8.2d
  fcvtmu v4.2d, v8.2d
  fcvtmu v5.2d, v8.2d
  fcvtmu v6.2d, v8.2d
  fcvtmu v7.2d, v8.2d
  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)03090b191e3f51inst 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)9fa0a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058155000327302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802042003915500078302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000003011151180160020036800001002004020040200402004020040
802042003915500063302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391560100302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000010011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
802052003915600012302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200899977699908012020280032200800322003920039118020110099100100800001000000011151180160020036800001002004020040200402004020040
80204200391550003302580108100800081008002050064013202002020039200399977699908012020080032200800382004820049118020110099100100800001000000022251281231120045800001002004920049200492004920049
8020420048155000123642780116100800161008002850064019602002920048200489976999868012820080038200800382004820048118020110099100100800001000000022251281231120045800001002004920050200492008920049
802042004816500045642680116100800161008002850064019602002920048200489976999868012820080038200800382004820048118020110099100100800001000000022251281231120045800001002005020049200492004920049

1000 unrolls and 10 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)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
8002420050156004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502015166172003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050205161772003680000102004020040200402004020040
8002420039155004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502016161762003680000102004020040200402004020040
8002420039155004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001010502013161782003680000102004020040200402004020040
8002420039155012402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050206161762003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050205166172003680000102004020040200402004020040
8002420039155004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502011161782003680000102004020040200402004020040
80024200391560040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020141617172003680000102004020040200402004020040
8002420039155004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502061623192003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050206161782003680000102004020040200402004020040