Apple M1 Microarchitecture Research by Dougall Johnson

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

UQXTN (8H)

Test 1: uops

Code:

  uqxtn v0.8b, v0.8h
  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)033f4e51inst 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
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
10043037226125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037226125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037229625472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037226125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037226125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqxtn v0.8b, v0.8h
  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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251621362954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
1020430037225396612954725101001001000010010000500427716013001830177300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
102043003722424612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
1020430037225181032954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
10204300372256612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129705100001003003830038300383003830038
102043003722533612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
102043003722512612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038
1020430037225241932954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010007101161129633100001003003830038300383003830038

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
10024300372250000342061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000285061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300842250000327061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000342061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229696010000103003830038300383003830038
10024300372250000165061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000345061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000024061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000312061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqxtn v0.8b, v8.8h
  uqxtn v1.8b, v8.8h
  uqxtn v2.8b, v8.8h
  uqxtn v3.8b, v8.8h
  uqxtn v4.8b, v8.8h
  uqxtn v5.8b, v8.8h
  uqxtn v6.8b, v8.8h
  uqxtn v7.8b, v8.8h
  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)030b18191e1f3a3f51inst 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)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000018600302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
80204200391500009300302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013212007020039200399977699908012020080032200800322003920039118020110099100100800001000010301115153160020036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
80204200391500001200302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
8020420039150000000722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040
80204200391500001200302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000001115118160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)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)9fa8accfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915002104025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
80024200391500904025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
8002420039150026404025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
80024200391500004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
80024200391500004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915001504025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
80024200391500004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915004204025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915006304025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040
800242003915001204025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100050201160112003680000102004020040200402004020040