Apple M1 Microarchitecture Research by Dougall Johnson

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

SQXTN (D)

Test 1: uops

Code:

  sqxtn s0, d0
  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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230101254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
10043037230158254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
10043037230145254725100010001000398160030183037303724143289510001000100030373037111001100020073216222629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073216122629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372218105254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
10043037232161254725100010001000398160030183037303724143289510001000100030373037111001100000073116222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100020073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqxtn s0, d0
  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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330261295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000307101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001281307101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225016629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225053829547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722508429547251001010100001010000504277160030018300373003728286328788100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225083329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225017929547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430084225091829547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722508429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722508429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722508429547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722508429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300853003830038

Test 3: throughput

Count: 8

Code:

  sqxtn s0, d8
  sqxtn s1, d8
  sqxtn s2, d8
  sqxtn s3, d8
  sqxtn s4, d8
  sqxtn s5, d8
  sqxtn s6, d8
  sqxtn s7, d8
  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)0318191e1f3f51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150000072258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151183164420036800001002004020040200402004020040
8020420039150000051258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163420036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000311151183164420036800001002004020040200402004020040
80204200391500021010830258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163220036800001002004020040200402004020040
8020420039150000051258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151183234420045800001002004920049200492004920049
80204200481500000642680116100800161008002850064019612002902004920049997610998680128200800382008003820048200481180201100991001008000010000022251294235520045800001002004920049200502004920050
8020420048151000064268011610080016100800285006401961200290200492004899769998680128200800382008003820048200481180201100991001008000010000022251285235720045800001002004920049200492004920050
8020420049150000064278011610080016100800285006401961200290200492004999769998680128200800382008003820049200491180201100991001008000010000022251284235420045800001002004920050200492004920049
80204200491500000539278011610080016100800285006401961200290200482004899769998680128200800382008003820048200481180201100991001008000010000022251293235420045800001002005020050200502004920049
8020420048150000064278011610080016100800285006401961200290200482004899769998680128200800382008003820048200481180201100991001008000010000022251284235420046800001002004920049200502004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150104025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020316272003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020216352003680000102004020040200402004020040
80024200391500040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001083605020216252003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020316372003680000102004020040200402004020040
80024200391500017225800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020216342003680000102004020040200402004020040
8002420039150008625800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020216342003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020216242003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000101005020316332003680000102004020040200402004020040
8002420039150006325800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020316332003680000102004020040200402004020040
80024200391500057825800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100005020216332003680000102004020040200402004020040