Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHRN (D)

Test 1: uops

Code:

  uqshrn 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030853037111001100000073216222629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303722061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100020073216222629100030383038303830383038
10043037220612547251000100010003981600301830373037241432895100010001000303730371110011000002173216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqshrn 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)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)9fa0a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722406129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296890100001003003830038300383003830038
1020430037225080729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225085229547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225089129547251010010010000100100005004277160130018300373003728264328745101002021000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383008430038
102043003722408229547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300863003830038
1020430037225081429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225086429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225014529547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225087729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402161229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000082295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037224000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001040000006402162229629110000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000251295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042785120300183003730037282863287671001020100002010000300373003711100211091010100001000000130506462342229670010000103003830038300383003830038
1002430037224000090061295384410010101000010100005042771600300183003730037282913287671001020100002010000300373003711100211091010100001000000306402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqshrn s0, d8, #3
  uqshrn s1, d8, #3
  uqshrn s2, d8, #3
  uqshrn s3, d8, #3
  uqshrn s4, d8, #3
  uqshrn s5, d8, #3
  uqshrn s6, d8, #3
  uqshrn 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): 0.2506

retire (01)cycle (02)0308191e1f3f51inst 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
8020420058150000065288011210080012100800245006401640200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251284241220046800001002005020050200502005020050
8020420049151000065288011210080012100800245006401641200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002005020050200502005020050
80204200491500000652880112100800121008002450064016412003020049200499976999888012420080034200800342004920049118020110099100100800001004420022251282241220046800001002005020050200502005020050
8020420049150000065288011210080012100800245006401640200302003920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002005020050200502005020050
8020420049150000065288011210080012100800245006401640200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002005020101201002005020050
8020420049150000065288011210080012100800245006401640200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002005020050200502005020050
8020420049150000065288011210080012100800245006401641200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002026420050200502005020050
8020420049150000065288011210080012100800245006401640200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002005020050200502005020050
80204200491500000350288011210080012100800245006401640200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002005020050200502005020050
8020420049150000065288011210080012100800245006401640200302004920049997699988801242008003420080034200492004911802011009910010080000100000022251282241220046800001002005020050200502005020050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500886258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020416122003680000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020216222003680000102004020040200402004020040
800242003915007052580010108000010800005064000020020020039200399996310019800102080000208000020039200391180021109101080000102705020116112003680000102004020040200402004020040
8002420039150061258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
800242003915001054258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400002002032003920039999631001980010208000020800002003920039118002110910108000010005020216222003680000102004020040200402004020040
80024200391500450258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020216112003680000102004020040200402004020040
80024200391500913258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
8002420039150040258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500898258001010800001080000506400002002002003920039999631001980010208000020800002003920039118002110910108000010005020216222003680000102004020040200402004020040