Apple M1 Microarchitecture Research by Dougall Johnson

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

UMAXV (vector, 8B)

Test 1: uops

Code:

  umaxv b0, v0.8b
  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
1004303722019525472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723019325472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722010725472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722025525472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722016825472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  umaxv b0, v0.8b
  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)0308090b18191e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000612954725101001001000010010000500427716003001830037300372826832874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250000007262954725101001001000010010000500427716003001830037300372826432876310100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250000003462954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010010071011611296330100001003003830038300383003830038
10204300372240000002512954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037224000000612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250000007262954744101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010121000810100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771603001830037300372828632876710010201000020200003003730037111002110910101000010000000006402162229629010000103008530038300383003830038

Test 3: throughput

Count: 8

Code:

  umaxv b0, v8.8b
  umaxv b1, v8.8b
  umaxv b2, v8.8b
  umaxv b3, v8.8b
  umaxv b4, v8.8b
  umaxv b5, v8.8b
  umaxv b6, v8.8b
  umaxv b7, v8.8b
  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)03080b191e1f3f51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151181160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010001311151180160020036800001002004020040200402004020040
80204200391500020030258010810080008100800205006401321200202003920039997769990801202008003220016027420039201121180201100991001008000010000011151180160120036800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132120020200392003999771710014801202008003220016006420039200391180201100991001008000010020611151180160020036800001002004020040200402004020040
802042003915000000502580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100005111151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010001011151180160020036800001002004020040200402004020040
80204200391500000072258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010001311151180160020036800001002004020040200402004020040
80204200391501006883025801081008000810080020500640132120020200392003999776999080120200800322001600642005120090218020110099100100800001000152311151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220016006420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e3f51inst 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)9fa8acbranch mispredict (cb)cficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100305020018166112003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020010166112003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001007205020011161262003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001001805020010166122003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020012161282003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020011166112003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050200121613132003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010011705020012161372003680000102004020040200402004020040
8002420039150000705258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001001505020012161162003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502005165102003680000102004020040200402004020040