Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTM (vector, 8H)

Test 1: uops

Code:

  frintm 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)030b18191e1f3f4e51inst 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
10043037230000082254725100010001000398160030183037303724143289510001000100030373037111001100010373216112629100030383038303830383038
100430372300000103254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300012061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230000061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240000081254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240000061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintm 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)0307080918191e1f3a3f4e51inst 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)6061696d6edispatch 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)9fa0a1a6a7a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232000000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000002030710021631296330100001003003830038300383003830038
1020430037233000000016129547251010010010000100100006264277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038302273003830038
10204300372320000090012629547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710031611296330100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
1020430037232000000006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
10204300372320000000044129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
1020430037233000003006129547251010010010000100100005004277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710011611296330100001003003830038300383003830038
1020430037233000000006329547251012512510000125100006264277160003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000714035211296330100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005004277160003001830037300372826432874510125200100002001000030037300371110201100991001001000010000000000710011621296330100001003003830038300383003830038

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)9fa7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000156402162229629010000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723200061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402169229629010000103003830038300383003830038
100243003723200061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723200061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723300661295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintm v0.8h, v8.8h
  frintm v1.8h, v8.8h
  frintm v2.8h, v8.8h
  frintm v3.8h, v8.8h
  frintm v4.8h, v8.8h
  frintm v5.8h, v8.8h
  frintm v6.8h, v8.8h
  frintm 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)03080a0b18191e1f3a3f51inst 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)9fa0a1a6a7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059155000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000123011151189160020036800001002004020040200402004020040
80204200391560100000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
8020420039155000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001102011151180160020036800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000011151180160020036800001002004020040200402004020040
802042003915500000120018725801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000189011151180160020036800001002004020040200402004020040
8020420039155000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000111011151180160020036800001002004020040200402004020040
802042003915500000000582580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000099011151180160020036800001002004020040200402004020040
802042003915500000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000066011151180160020036800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000003011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030809181e3a3f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020616742003680000102004020040200402004020040
8002420039156000120402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020616672003680000102004020040200402004020040
800242003915500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020316432003680000102004020040200402004020040
800242003915600000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020716442003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020716442003680000102009220091200402004020040
800242008915600000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020516432003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020816742003680000102004020040200402004020040
800242003916100000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020416342003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020416342003680000102004020040200402004020040
800242003915500000822580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020731462003680000102004020040200402004020040