Apple M1 Microarchitecture Research by Dougall Johnson

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

SQXTN (2D)

Test 1: uops

Code:

  sqxtn v0.2s, v0.2d
  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
100430372236125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372296125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110002073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqxtn v0.2s, v0.2d
  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)9fa0a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954725101001001002410010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010020007102161229633100001003003830038300383003830038
102043003722501072954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372259822954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372240842954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250822954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722501072954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722501072954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722501722954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722508429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225019129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250266929547251001010100001010000504277160030018300373003728286328767100102010167201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225021429547251001010100001210000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225054729547251001010100001010000504277160030018300373008428286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225023329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225035629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722508229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqxtn v0.2s, v8.2d
  sqxtn v1.2s, v8.2d
  sqxtn v2.2s, v8.2d
  sqxtn v3.2s, v8.2d
  sqxtn v4.2s, v8.2d
  sqxtn v5.2s, v8.2d
  sqxtn v6.2s, v8.2d
  sqxtn v7.2s, v8.2d
  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)03091e3f51inst 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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150007262580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100011151181160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020040
802042003915001627952580108100800081008002050064013202002020039200399977069990801202008003220080032200392003911802011009910010080000100111151180160020036800001002004020040200402004020040
8020420039150007792580108100800081008002050064013212002020039200399977069990801202008003220080032200392003911802011009910010080000100011151180160020036800001002004020040200402004020049
802042004815000642780116100800161008002850064019602002920048200489976099986801282008003820080038200492004911802011009910010080000100022251291231120046800001002004920050200492004920049
802042004815000642780116100800161008002850064019612002920049200489976099986801282008003820080038200482004911802011009910010080000100022251281231120046800001002004920049200502004920049
8020420048150006426801161008001610080028500640196020029200482004999760109986801282008003820080038200492004811802011009910010080000100022251281231120046800001002005020050200502004920049
802042004815000642780116100800161008002850064019602002920049200489976099986801282008003820080038200492004811802011009910010080000100022251291231120046800001002004920049200492005020049
8020420049150006427801161008001610080028500640196120029200492004999760109986801282008003820080038200492004911802011009910010080000100022251281231120045800001002005020049200492004920049
80204200491501012726801161008001610080028500640196020029200482004999760109986801282008003820080038200482004811802011009910010080000100022251281231120045800001002004920050200492004920050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3a3f51inst 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)5f60696d6edispatch 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)9fa0a8acc2cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000001682580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010069050201160112003680000102004020040200402004020040
800242003915000000822580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
800242003915000000822580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
800242003915000000612580010108000010800005064000001200202003920039999631001980123208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
80024200391500000010022580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
8002420039150000005222580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
8002420039150000001072580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
800242003915000000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
800242003915000000612580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
800242003915000000402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040