Apple M1 Microarchitecture Research by Dougall Johnson

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

SMAXV (vector, 8H)

Test 1: uops

Code:

  smaxv 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)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
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110001073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073116222629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
1004303722021025472510001000100039816003018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372206125474310001000100039816013018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  smaxv 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)0318191e1f3f4e51inst 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)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021611296330100001003003830038300383003830038
1020430037224000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000726295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250000726295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830083
10204300372250000103295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa0a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722505272954725100101010000101000050427716030018300373003728300328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722402082954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722503762954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722501702954725100101010000101000050427716030018300373003728286328767100102010000202034430037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722505702954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722404632954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722501072954725100101010000101000050427716030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  smaxv h0, v8.8h
  smaxv h1, v8.8h
  smaxv h2, v8.8h
  smaxv h3, v8.8h
  smaxv h4, v8.8h
  smaxv h5, v8.8h
  smaxv h6, v8.8h
  smaxv 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)0318191e1f3f51inst 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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500000512580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511811620036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132020020200392003999776100248012020080032200160064200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500000532580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000100111511801620036800001002004020040200402004020040
80204200391500000512580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
802042008915000001352580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
802042003915000001252580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000100111511801620036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f3a3f51inst 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)9fa8a9accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500000126258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050209160632003680000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050202160422003680000102004020040200402004020040
80024200391500000359258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202160242003680000102004020040200402004020040
8002420039150000082258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001010050204160422003680000102004020040200402004020040
800242003915000021170258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050204160242007780000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050203160422003680000102004020040200402004020040
80024200391500300322258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050204160242003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001010050205160652003680000102004020040200402004020040
8002420039150000061258001010800981080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050203160242003680000102004020040200402004020040
80024200391560000497258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050204160422009780000102004020040200402004020040