Apple M1 Microarchitecture Research by Dougall Johnson

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

SQABS (scalar, H)

Test 1: uops

Code:

  sqabs h0, h0
  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)696d6edispatch 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723082254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073216112629100030383038303830383038
10043037221261254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004308423061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073216112629100030383038303830383038
1004303722061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730372110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs h0, h0
  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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071021611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100002471011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710116112963317100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722400612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129547251001010100001010600764285272130234303683037028307282889810915201097922111373036630415811002110910101000010243221960127884735329878310000103032130368303553036930368
10024303572280167924616409729493155100381510056141105060428662403001830369304042831237288961106626111672011140303693032181100211091010100001000000006402162229860310000103036730369303663037030371
100243027422810769246164751294841541005914100561710750874285272030198304163046428317372891911216221134624113053041430415911002110910101000010000002484028305452229973310000103045530415304173041630504
1002430412228111010132988077872949320910101151010415118007142893280304503065130643283333328948118152810972221179930462305021311002110910101000010020703112006402162229845610000103064030514304183050130510
100243054823600000061295472510010101000010100005042771600300183003730037282863287671001020100002010000302273003711100211091010100001000000606402162229667010000103003830038300383003830038
1002430037233000030612954725100101010000101000050427716003001830037300702828632876710010201000020100003003730037111002110910101000010000007806402162229629010000103003830038300383003830038
1002430037233000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000008106402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000008106402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000002706402162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000008706402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqabs h0, h8
  sqabs h1, h8
  sqabs h2, h8
  sqabs h3, h8
  sqabs h4, h8
  sqabs h5, h8
  sqabs h6, h8
  sqabs h7, h8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)033f51inst 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)9fa0a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511811600200360800001002004020040200402004020040
8020420039150288258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
8020420039150757258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801610200360800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
80204200391504781258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
80204200391613025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000530111511801600200360800001002004020040200402004020090
802042003915030258010810080085100800205006401322002020039200399987699908012020080032200802472003920039118020110099100100800001000000111513504400200360800001002009820112201142010220113
802042011515130258030610280104100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915072258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e1f3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000001662580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020416442003680000102004020040200402004020040
80024200391500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100305020216422003680000102004020040200402004020040
800242003915010004672580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020416442003680000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001115020416422003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020416242003680000102004020040200402004020040
80024200391500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020216422003680000102004020040200402004020040
80024200391500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020216242003680000102004020040200402004020102
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020416422003680000102004020040200402004020040
800242003915000007052580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020216442003680000102004020040200402004020040
80024200391500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020416422003680000102004020040200402004020040