Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHRUN (D)

Test 1: uops

Code:

  sqshrun s0, d0, #3
  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)a8acc3cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722082254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqshrun s0, d0, #3
  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)0318191e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400111061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250039061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003008330037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250027061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037224000061295472510100100100001001000050042771600300543003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250024061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372250012061295472510100100100001001000050042771600300183003730037282643287451010020010000202100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225003061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

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)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
1002430037225906129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722503526129547251001010100001010000504277160300183003730037282863287671001020100002010161300853008411100211091010100001000669216222962910000103003830038300383003830038
10024300372256906129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372255706129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372253006129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000640216222969610000103003830038300383003830038
1002430037225606129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722503526129547251001010100001010000504277160300183003730037282863287671001020100002010162300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010480640216222962910000103003830038300383008530038
1002430037225606129547251001010100001010000504277160300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300853008530038
1002430037225660612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100120640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqshrun s0, d8, #3
  sqshrun s1, d8, #3
  sqshrun s2, d8, #3
  sqshrun s3, d8, #3
  sqshrun s4, d8, #3
  sqshrun s5, d8, #3
  sqshrun s6, d8, #3
  sqshrun s7, d8, #3
  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)0318191e3f51inst 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
8020420058150009302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402008920040
8020420039150000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500024302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500036302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500006426801161008001610080028500640196020029200482004899769100138012820080038200800382004820048118020110099100100800001000022251281231120045800001002005020049200492004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa1a6a9accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050204160432003680000102004020040200402004020040
800242003915000006040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050206160432003680000102004020040200402004020040
800242003915000002100515258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050204160432003680000102004020040200402004020040
80024200391501040300061258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050204160362003680000102004020040200402004020040
800242003915000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050207160442003680000102004020040200402004020040
800242003914900000061258001010800001080000506400000200442003920039999631001980010208000020800002003920039118002110910108000010000050206160342003680000102004020040204002009820040
80024200391500000240402580010108000010800005064000002002020039200391002431001980010208000020800002003920039118002110910108000010000175050207160642003680000102035320553205002004020040
800242003915511000040258001010800001080000506400000200202003920039999631001980010208000020800002003920103118002110910108000010000350206160662003680000102004020040200402004020040
8002420039155000017281144219122781085128126610811365064810402050520710206131010652103688105620812472081260207022064713180021109101080000102325665521881250562043780000102004020040200402004020040
80024200391550000480381438001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050206160662003680000102004020040200402004020040