Apple M1 Microarchitecture Research by Dougall Johnson

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

SQADD (vector, 16B)

Test 1: uops

Code:

  sqadd v0.16b, v0.16b, v1.16b
  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)030b191e1f3f4e51inst 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
100430372300006125482510001000100039831303018303730372415328951000100020003037303711100110000073216112630100030383038303830383038
100430372300006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372300006125482510001000100039831313018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
1004303723000061254825100010001000398313030183037303724153289510001000200030373037111001100004273116112630100030383038303830383038
1004303722000014725482510001000100039831303018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
100430372300006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372300006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372200006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372200006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372200006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqadd v0.16b, v0.16b, v1.16b
  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)030809191e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001005071011611296340100001003003830038300383003830038
1020430037225000082295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000671011611296340100001003003830038300383003830038
102043003722500001352295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001003071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001001071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3a3f4e51inst 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)696b6d6edispatch 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250262295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001036064481610102963010000103003830038300383003830038
1002430037225026229548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000105090644121611102963010000103003830038300383003830038
100243003722502622954825100101010000101000050427731330054030037300372828732876710010201000020200003003730037111002110910101000010000644101610102963010000103003830038300383003830038
100243003722502622954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010250064410161042963010000103003830038300383003830038
1002430037225026229548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000105515064410165102963010000103003830038300853003830038
100243003722402622954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010500064451610102963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001058120644101612122963010000103003830038300383003830038
1002430037225026229548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000104090644101610102963010000103003830038300383003830038
100243003722502622954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010090644101610102963010000103003830038300383003830038
100243003722592622954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010000644516882963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqadd v0.16b, v1.16b, v0.16b
  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)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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502512954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001003007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010023317101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001002007101161129634100001003003830038300383003830038
102043003722507262954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001001007101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)72scheduler 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
100243003722500000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001050640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250000026572954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001056640216222963010000103003830038300383003830038
100243003722400000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001026640216222963010000103003830038300383003830086
100243003722400000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001030640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001013640216222963010000103003830038300383003830038
100243003722400000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001003640216222963010000103003830038300383003830038
100243003722400000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000007262954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001020640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqadd v0.16b, v8.16b, v9.16b
  sqadd v1.16b, v8.16b, v9.16b
  sqadd v2.16b, v8.16b, v9.16b
  sqadd v3.16b, v8.16b, v9.16b
  sqadd v4.16b, v8.16b, v9.16b
  sqadd v5.16b, v8.16b, v9.16b
  sqadd v6.16b, v8.16b, v9.16b
  sqadd v7.16b, v8.16b, v9.16b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030818191e1f3f51inst 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
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051102161120036800001002004020040200402004020040
80204200391500000010425801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000006225801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)5f60696d6edispatch 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)9fa8a9acc5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150006125800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200416422003680000102004020040200402004020040
80024200391500051525800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200416252003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200416242003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200216442003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200416422003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010003050200216442003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200416422003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200216442003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200416242003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200616432003680000102004020040200402004020040