Apple M1 Microarchitecture Research by Dougall Johnson

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

SMULL2 (vector, 2D)

Test 1: uops

Code:

  smull2 v0.2d, v0.4s, v1.4s
  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
1004303722010325482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
100430372308225482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
1004303722010725482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  smull2 v0.2d, v0.4s, v1.4s
  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)03091e3f4e51inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722501266129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009901001001000010000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009901001001000010000071011611296340100001003003830038300383003830038
10204300372250246129548251010010010000100100005004277313130065300373003728265328745101002001000020020000300373003711102011009901001001000010000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099010010010000100000710116112963418100001003003830038300383003830038
1020430037225066129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009901001001000010000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009901001001000010000071011611296340100001003003830038300383003830038
10204300372250876129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009901001001000010000071011611296340100001003003830038300383003830038
10204300372250156129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300843003711102011009901001001000010000071011611296920100001003003830038300383003830038
10204300372250216129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009901001001000010013071011611296340100001003003830038300383003830038
10204300372250053629548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009901001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e3f4e51inst 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
10024300372250000516129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002530037225000036129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000336129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000186129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018030037300372830532876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000010006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  smull2 v0.2d, v1.4s, v0.4s
  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)03090b18191e3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000286029548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101163129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240000306129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000036129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000107101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa1a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250007206129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372251002406129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010001006402162229630010000103003830038300383003830038
1002430037224000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000036402162229630010000103003830038300383023030038
100243003722500015074729548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250003306129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010003006402162229630010000103003830038300383003830038
1002430037225000306129548251001010100001010000504277313030018030037300842828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250009061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100000486402162229630010000103003830038300383003830038
1002430037224000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003012130085111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  smull2 v0.2d, v8.4s, v9.4s
  smull2 v1.2d, v8.4s, v9.4s
  smull2 v2.2d, v8.4s, v9.4s
  smull2 v3.2d, v8.4s, v9.4s
  smull2 v4.2d, v8.4s, v9.4s
  smull2 v5.2d, v8.4s, v9.4s
  smull2 v6.2d, v8.4s, v9.4s
  smull2 v7.2d, v8.4s, v9.4s
  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)03080918191e1f3f51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511021611200360800001002004020040200402004020040
80204200391500000006992580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000060412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3a3f51inst 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)9fa8accfd0d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915020040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502002160442003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502007160352003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502003160332003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502005160432003680000102004020040200402004020040
80024200391500267040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502004160442003680000102004020040200402004020040
8002420039150018040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502005160352003680000102004020040200402004020040
8002420039150012040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502003160432003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502004160442003680000102004020040200402004020040
8002420039150000149258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502004160442003680000102004020040200402004020040
8002420039150000147258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502002160342003680000102004020040200402004020040