Apple M1 Microarchitecture Research by Dougall Johnson

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

SQXTUN (S)

Test 1: uops

Code:

  sqxtun h0, s0
  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
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372208225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqxtun h0, 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)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)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
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001001071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000371011611296330100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000671011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000000164021622296290010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000000064021622296290010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000000064021622296290010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000000064021622296290010000103003830038300383003830038
10024300372250000061295472510010101000010100006042785121300183003730037282863287671001020100002010000300373003711100211091010100001000000000064021622296290010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000000064021622296290010000103003830038300383003830038
100243003722500000346295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000000064021622296290010000103003830038304153046330508
1002430463228049120088037792945522810084131007215112005042906800303783026330546283193828955116802211636221163130556302731111002110910101000010402227925200064021622296290010000103003830038300383003830038
100243003722509913207922695294572091010517100881511500824290378030414304633017828326442886111514301164624116333023230037111002110910101000010002032000830410143299534010000103051030560303223051130559
1002430549227010101323880644829457211101071110080151150012542906801303423055930462283294628858115102011478201163430546305061111002110910101000010001002000852511035299918010000103035830513305123051330415

Test 3: throughput

Count: 8

Code:

  sqxtun h0, s8
  sqxtun h1, s8
  sqxtun h2, s8
  sqxtun h3, s8
  sqxtun h4, s8
  sqxtun h5, s8
  sqxtun h6, s8
  sqxtun h7, s8
  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)03080b181e1f3f51inst 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)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000012030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001011151180160020036800001002004020040200402004020040
802042003915000000302580108100800081008002050064013212002020039200399977610015801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000024030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000311151180170020036800001002004020040200402004020040
80204200391500006030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
8020420039150000381030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000611151180160020036800001002004020040200402004020040
80204200951500012460118258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100030011151180160020036800001002004020040200402004020040
8020420039150000465030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3a3f51inst 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)9fa7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005116100004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020316332003680000102004020040200402004020040
800242003915004800402580010108000010800005064000012002002003920039999631001980010208000020800002003920039118002110910108000010000586005020516442003680000102004020040200402004020040
8002420039150039004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020416342003680000102004020040200402004020040
80024200391500444004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020316332003680000102004020040200402004020040
8002420039150000040258001010800001080000506400001200200200392003999963100198001020800002080000200392003911800211091010800001003700005020316442003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020516552003680000102004020040200402004020040
80024200391500105004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020416452003680000102004020040200402004020040
8002420039150000070525800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020416442003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020416342003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100000005020416552003680000102004020040200402004020040