Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINV (8H)

Test 1: uops

Code:

  fminv h0, 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)030b1e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722006125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722006125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230010325472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722008225472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230063325472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722006125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fminv h0, 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)03191e1f3f4e51inst 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
102043003722500025129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100037101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000907101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000817101161129633100001003003830038300383003830038
1020430037225000156295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000967101161129633100001003003830038300383003830038
102043003722410061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000787101161129633100001003003830038300383003830038
10204300372250007472954725101001001000010010000500427716003001830037300372826425287451010020010000200100003003730037111020110099100100100001000667101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000967101161129633100001003003830038300383003830038
102043003722500025129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100067101161129633100001003003830038300383003830038
1020430037225000346295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000937101161129633100001003003830038300383003830038
1020430037225000346295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000847101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000240306402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000250306402162229629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000300606402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000250306402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001803003730037282863287671001020101722010000300373003711100211091010100001000002801120806402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001803003730037282862728767100102010000201000030037300371110021109101010000100000280306402162229629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000280306402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018030037300372829732876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000280306402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001803003730037282863287671001020100002010000300373003711100211091010100001000003001095806402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fminv h0, v8.8h
  fminv h1, v8.8h
  fminv h2, v8.8h
  fminv h3, v8.8h
  fminv h4, v8.8h
  fminv h5, v8.8h
  fminv h6, v8.8h
  fminv h7, 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)03071e3f51inst 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)9fa0a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100003011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802021009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000456011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100020011151180160020036800001002004020040200402004020040
80204200391490030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8a9acbranch mispredict (cb)cfd5d6daddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000050202516013252003610480000102004020040200402004020040
800242003915005152580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020251602526200368880000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020251602525200366780000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020251601426200366780000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020241602525200368880000102004020040200402004020040
800242003915009352580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020251602025200368880000102004020040200402004020040
800242003915006102580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005043141602420200368880000102004020040200402004020040
80024200391500402580010108009910800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020251602625200368880000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020251601424200368780000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020261601625200368780000102004020040200402004020040