Apple M1 Microarchitecture Research by Dougall Johnson

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

UQADD (scalar, S)

Test 1: uops

Code:

  uqadd s0, s0, s1
  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
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073216112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303721100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd s0, s0, s1
  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)030818191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000006129548251010010010000100100005004277313030018300373003728293328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250110006129539441012113010016118101495004277313130018300373003728265328745102712001000020020000300373003711102011009910010010000100000000075611611296340100001003003830038300383003830038
102043003722506679261614513295391461018514110056138110436454286736030234303693036428276352886911144222111652262211030321304178110201100991001001000010040201416803867280212974230100001003037230133303753032630370
102043013122813792761604558294941631019514110048139110437184285342030234305073037128272312887410576226111392242202630357303688110201100991001001000010002202019510877380222988724100001003032330370303723040930370
1020430366227187933616116829548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722400015006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000010329548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640416222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313301623003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722509429548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183013230037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd s0, s1, s0
  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)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
1020430037225000001200612954825101001321000010010000500427731330018300373003728265328745102672001016520020334301823008521102011009910010010000100000103271011612296340100001003003830038300383003830038
1020430037225000001200612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000100071011611296340100001003003830038300383003830038
1020430037225000000001032954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000100071011611296340100001003003830038300383003830038
10204300372250000000021522954825101001001000010010000500427731330018300373003728269328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000000010442946424810209150100721431163978342908833037830509305142830150289421164523511652234229723051230513111102011009910010010000100000102780509372105213000735100001003051230551305163051030515
1020430552229001101014619681746329458220102191511008015110596798429088330378304993031228301452885511501233113242302298630511305151011020110099100100100001002021224875071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000000271011611296340100001003003830038300383003830038
10204300372250000000058152954825101001001000010010149500427867030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010000640416552963010000103003830038300383003830038
1002430037225174612954825100101010000101000050427731330018030037300372828732876710010221000020200003003730037111002110910101000010000640516662963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010000640616562963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010000640616562963010000103003830038300383003830038
10024300372250612954825100101210000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010000640616652963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010010640516562963010000103003830038300383003830038
100243003722503432954825100101010000101014950427731330018030037300372828732876710010201000020200003003730037111002110910101000010019640516652963010000103003830038300383003830038
100243003722502512954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010013640616462963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010000640516562963010000103003830038300383003830038
100243003722502512954825100101010000101000050427731330018030037300372828732876710010201000020200003003730037111002110910101000010000640616562963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd s0, s8, s9
  uqadd s1, s8, s9
  uqadd s2, s8, s9
  uqadd s3, s8, s9
  uqadd s4, s8, s9
  uqadd s5, s8, s9
  uqadd s6, s8, s9
  uqadd s7, s8, s9
  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)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)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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815100004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100020051102161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000120020020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000004180801001008000010080000500640000120020020039200399973399978010020080000200160000200392003911802011009910010080000100010051101161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000120020020039200399973399978010020080000200160000200392003911802011009910010080000100000351101161120036800001002004020040200402004020040
8020420039150000032625801001008000010080000500640000120020020039200399973399978010020080000200160000200392003911802011009910010080000100030051101161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000004125801001208000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000351101371120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000020020020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e3f51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001002800050205165520036080000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208010620160000200392003911800211091010800001003109050206165520036080000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100100050204164520036080000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100100050206164520036080000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100100050205164520036080000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010010946050205167520036080000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001001706050205165520036080000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999626100198001020800002016000020039200391180021109101080000100200050207166520036080000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000050206165520036080000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000050206165520036080000102004020040200402004020040