Apple M1 Microarchitecture Research by Dougall Johnson

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

ABS (vector, D)

Test 1: uops

Code:

  abs d0, d0
  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)03191e1f3f4e51inst 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)a6a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018308530372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037231906125472510001000100039816013018303730372414328951000100010003037303711100110000073116112658100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  abs d0, d0
  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)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)9fa1a8acc2c5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722504292954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10205300372240612954725101001001000010010149500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10204300372240612954725101141001000810010000500427716003001830037300372826473287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
1020430037225018192954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10204300372250148529547251010010010000100100005824277160030018300373003728264032874510100200100002001000030037300371110201100991001001000010000180007102162229633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10204300372250612954743101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10205300372250612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000100007102162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225002060295472510010101000010100005042771601300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225001161295472510010101000010100005042771601300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225001189295472510010101000010100005042771601300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103022830038300383003830038
1002430037225001786295472510010101000010100005042771601300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225001212295472510010101000010100005042771600300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300180300373003728286732876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225001987295472510010101000010100005042771600300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250881932295472510010101000010100005042771600300180300373003728286032876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383013330038
100243003722500886295472510010101000010100005042771601300180300373003728286032878610010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  abs d0, d8
  abs d1, d8
  abs d2, d8
  abs d3, d8
  abs d4, d8
  abs d5, d8
  abs d6, d8
  abs d7, d8
  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)031e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815105472580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200899977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500532580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999771299908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001002011151180160020036800001002004020091200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001002011151180160020036800001002004020040200402004020040
802042003915008992580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915001142580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308181e3f51inst 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)9fa8cdcfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100050203160112008680000102004020040200402004020040
800242003915000082258001010800001080000506400002002020039200399996310019801142080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915000061258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
8002420039150002740258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402008920040
800242003915000082778039610800001080319506400002002020039200399996310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915000061258001010800001080000506400002002020039200399996310019800102080107208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
80024200391500005102258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040