Apple M1 Microarchitecture Research by Dougall Johnson

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

UABD (vector, 8B)

Test 1: uops

Code:

  uabd v0.8b, v0.8b, v1.8b
  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)030a1e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037220061254825100010001000398313130183037303724153289510001000200030373037111001100020073116112630100030383038303830383038
100430372303961254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037220661254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037220061254825100010001000398313130183084303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372204561254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037220061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037231061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uabd v0.8b, v0.8b, v1.8b
  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)0308090b18191e1f3a3f4e51inst 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
102043003722500000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038
102043003722400000000962954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000200071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038
102043003722500100000612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200200003003730037111020110099100100100001000000100071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e3f4e51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300732251001326129548441001010100001010000504277313300183003730084282873287671001020100002020000300853003711100211091010100001004028194640316432963010000103003830038300383008430086
100243003722500113261295482510019101000010100005042773133001830037300842828732876710159201016320200003003730037111002110910101000010018000640316532963010000103003830038300383003830085
1002430037225000061295482510010101000010100005042773133001830037300852828732876710010201000020200003003730084111002110910101000010000139180640316332963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010033000640316332963010000103003830038300383003830038
10024300372250134126129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001001000640316332963010000103003830038300383003830038
100243003722400006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001003000640316332963010000103003830038300383003830038
1002430037224000061295482510010101000010100005042773133001830037300372828711287671001020100002020000300373003711100211091010100001001000640316332963010000103003830038300383003830038
1002430037225010061295484410010101000010102985042786703001830132301692828732876710010201000020200003003730037111002110910101000010010150640316332963010000103003830038300383003830038
1002430037232000061295031041005510100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000640316332963010000103008630038300383003830038
1002430037233000961295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010049000640316332963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uabd v0.8b, v1.8b, 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)030b1e3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000020071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000540071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225036129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773133001830037301332826532874510127200100002002033230037300371110201100991001001000010000000710116112967018100001003003830134302303003830133
1020430084225096129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282743287451010020010000200200003003730037111020110099100100100001000200071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000010071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030408090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400000000262295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000000644816101029630010000103003830038300383003830038
1002430037225000000002622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000120644516111129630010000103003830038300383003830038
1002430037224000000002622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000306441016101029630010000103003830038300383003830038
1002430037225000000002622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006441016101029630010000103003830038300383003830038
1002430037225000000002622954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010020010006441016111129630010000103003830038300383003830038
100243003722500000000262295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000000644111611829630010000103003830038300383003830038
100243003722500000000262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000000644516101129630010000103003830038300383003830038
1002430037225000000002622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006441016101029630010000103003830038300383003830038
100243003722500000000262295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000000644516101029630010000103003830038300383003830038
100243003722500000000262295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001020000000644101651029630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uabd v0.8b, v8.8b, v9.8b
  uabd v1.8b, v8.8b, v9.8b
  uabd v2.8b, v8.8b, v9.8b
  uabd v3.8b, v8.8b, v9.8b
  uabd v4.8b, v8.8b, v9.8b
  uabd v5.8b, v8.8b, v9.8b
  uabd v6.8b, v8.8b, v9.8b
  uabd v7.8b, v8.8b, v9.8b
  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)0304191e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150100622580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051104165520036800001002004020040200402004020040
802042003915000541672580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051104164420036800001002004020040200402004020040
8020420039150000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051105164520036800001002004020040200402004020040
80204200391500001042580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000651105165420036800001002004020040200402004020040
80204200391500001752580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165420036800001002004020040200402004020040
8020420039150000622580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051104165420036800001002004020040200402004020040
8020420039150000672580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001004051104165420036800001002004020040200402004020040
8020420039150000642580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165520036800001002004020040200402004020040
80204200391500004102580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165420036800001002004020040200402004020040
8020420039150000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051105165520036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a181e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000661258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000101305020516352003680000102004020040200402004020040
8002420039150000187258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516532003680000102004020040200402004020040
800242003915000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516532003680000102004020040200402004020040
800242003915000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516632003680000102004020040200402004020040
800242003915000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516352003680000102004020040200402004020040
800242003915000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020616532003680000102004020040200402004020040
800242003915100040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020316352003680000102004020040200402004020040
800242003915000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005045516552003680000102004020040200402004020040
800242003915000061258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516352003680000102004020040200402004020040
8002420039150002440258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100005020316352003680000102004020040200402004020040