Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTI (scalar, H)

Test 1: uops

Code:

  frinti h0, h0
  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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037241861254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037233961254725100010001000398160130183037303724143289510001000100030373037111001100000073116112642100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240884254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinti h0, h0
  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)030b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330001200103295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000192071011611296330100001003003830038300383003830038
1020430037233000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000400071011611296330100001003003830038300383003830038
10204300372470000006129547251010010010000100100005004277160300183003730037282643287451010020010000200106583003730037111020110099100100100001000003012071011611296330100001003003830038300383003830038
102043003723300000010329547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000005300071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000005100071011611296330100001003003830038300383003830038
10204300372320000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000004400071011611296330100001003003830038300383003830038
10204300372340000008929547251010010010000100100005004277160300543003730037282643287451010020010000200100003003730037111020110099100100100001000001200071011611296330100001003003830038300383003830038
102043003723300000017229547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000004900071011611296330100001003003830038300383003830038
10204300372330000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000004600071011611296330100001003003830038300383003830038
1020430037232000000199629547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000004600071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722501061295472510010101000010100005042771600300180300843008428300328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500061295472510010101000510100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300180300373003728286328767100102210000201000030037300371110021109101010000100006402162229629010000103008530038300383003830038
100243003722500061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243008422500061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722510061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100306402162229629010000103003830038300383003830038
1002430037225000887295473710010101000010100005042771601300183300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830086300383003830038
100243003722500061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinti h0, h8
  frinti h1, h8
  frinti h2, h8
  frinti h3, h8
  frinti h4, h8
  frinti h5, h8
  frinti h6, h8
  frinti h7, h8
  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)0307191e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915600128532580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550009512580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550004952580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
80204200391550008032580108100800081008002050064013212005920039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550001602580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180164420036800001002004020040200402004020040
80204200391550002582580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550008202580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180161020036800001002004020040200402004020040
80204200391550008542580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180161120036800001002004020040200402004020040
802042003915600010212580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000311151200160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cficache miss (d3)d5d6dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391560000006125800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000027000502008160057200360080000102004020040200402004020040
8002420039155000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502005160065200360080000102004020040200402004020040
80024200391550000003312580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502005160055200360080000102004020040200402004020040
800242003915600000070525800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000047000502006160066200360080000102004020040200402004020040
80024200391550000004044801091080195108010550640816120063201032009710003121004680108228020420800002009020151218002110910108000010202045522503808340085200840080000102004020040200402004020040
80024200391550111321081237448010810800981080098506407760200692009320089100067100468011520800992080099200992009121800211091010800001004000870502005160088200360080000102004020040200402004020040
8002420039155000300054066802061080099108009950640000020020200392003999967100198001020800002080000200392003911800211091010800001000000962502008160056200360080000102004020040200402004020098
80024200911570001500402580010108000010800005064000002033120148201069996710075801082080105208010420098200391180021109101080000100001030502008160058200360080000102004020040200402004020040
8002420039155000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502007160065200360080000102004020040200402004020040
8002420039150000900402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100002000502008160056200360080000102004020040200402004020040