Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHRN (D)

Test 1: uops

Code:

  uqrshrn 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612547251000100010003981600301830373037241432895100010001000303730371110011000001273116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037221261254725100010001000398160030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372327061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037221261254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshrn 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)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)696b6d6edispatch 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
1020430037225061295472510100100100001001000050042771603001803003730037282643287451010020010000200100003003730037111020110099100100100001005200007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100301007101171129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018030037300372826432874510100200100002001000030037300371110201100991001001000010063210007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000007791161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771603001803003730037282643287451010020010000200100003003730037111020110099100100100001005030007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771603001803003730037282643287451010020010000200100003003730037111020110099100100100001004000007101161129633100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771603001803003730037282643287451010020010000200100003003730037111020110099100100100001002800007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771603001803003730037282643287451010020010000200100003003730037111020110099100100100001002500007101161129633100001003003830038300383003830038
1020430037225061295472510100100100081001000050042771603001803003730037282643287451010020010000204100003003730037111020110099100100100001000960007101161129633100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771603001803003730037282643287451010020010000200100003003730037111020110099100100100001003790007101161129633100001003003830038300383003830038

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)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)9fa0a1a6a8a9acc2c5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100000060006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300650300373003728286328767100102010000201000030037300371110021109101010000100000000106402162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601300183300373003728286328767100102010000201000030037300371110021109101010000100000002006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100001030006402162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100003030006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100004060006402169429881410000103036930324303693037030371
10024303682270167924616458029484851006916100481610900664286798130270030370303202831334289001106526103242011159303713035881100211091010100001040210186614007745734429881110000103041630367303693041830320
1002430367228000001086129529251001010100001110000504277160130270030371303682831731288971106826113052211144301323041771100211091010100001022800193682007885854429881410000103041730415304083037130417
1002430409227117793670458502947519510073161006413113385542825681303060302263045228318382882311217221148320114643046430449101100211091010100001000219254362007036485430025310000103064730547305943059330548
100243027522811511146188070712945722510092181000010100005042771601300180300373003728286328767100102010000201000030037300371110021109101010000100026122221500083031054529919310000103036930559301803032130418

Test 3: throughput

Count: 8

Code:

  uqrshrn s0, d8, #3
  uqrshrn s1, d8, #3
  uqrshrn s2, d8, #3
  uqrshrn s3, d8, #3
  uqrshrn s4, d8, #3
  uqrshrn s5, d8, #3
  uqrshrn s6, d8, #3
  uqrshrn 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): 0.2505

retire (01)cycle (02)03070a0b18191e1f3f51inst 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)9fa0a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150110000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151185165520036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151184165420036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151185164520036800001002004020040200402004020040
80204200391501100000160258010810080008100800205006407880200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151185164520036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151183165420036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151185164520036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151184164520036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151185165420036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151185164520036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151184164420036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f5051inst 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)9fa0a8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)dfe0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000402002325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005024391671732003680000102004020040200402004020040
800242003915000400258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050243171661732003680000102004020040200402004020040
8002420039150004002580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502431716171732003680000102004020040200402004020040
800242003915000400258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050243171661632003680000102004020040200402004020040
8002420039150004002580010108000010800005064000002006120039200399996310019800102080000208000020039200391180021109101080000100000504131716171732003680000102004020040200402004020040
8002420039150004002580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502431716141732003680000102004020040200402004020040
800242003915000400258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050243171661732003680000102004020040200402004020040
80024200391490082025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005024371681732003680000102004020040200402004020040
800242003915000400258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050243171617732003680000102004020040200402004020040
80024200391500040043801091080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005024381681832003680000102004020040200402004020040