Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHRN (S)

Test 1: uops

Code:

  uqrshrn h0, s0, #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)0318191e3f4e51inst 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
100430842211061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372200061254725100010001000398160130183037303724143289510001025100030373084111001100000073116112629100030383038303830383038
1004303722000210254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723000334254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372200061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372200061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshrn h0, s0, #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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001001834307103162229633100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
10204300372250124295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102162229696100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa1a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640416222962910000103003830038300383003830038
100243003722500726295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250013352952960100281510016121030071427986403005430131301322829412288051031422103222010326301693013231100211091010100001001300640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000300640216222962910000103008430038300383003830038
10024300372250061295472510010101000012100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqrshrn h0, s8, #3
  uqrshrn h1, s8, #3
  uqrshrn h2, s8, #3
  uqrshrn h3, s8, #3
  uqrshrn h4, s8, #3
  uqrshrn h5, s8, #3
  uqrshrn h6, s8, #3
  uqrshrn h7, s8, #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)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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039150000000302580108100800081008002050064013212002920048200489976109986801282008003820080038200482004811802011009910010080000100000060222512832311200450800001002004920050200492004920050
802042004815000000064268011610080016100800285006401961200292004820048997699986801282008003820080038200482004811802011009910010080000100000030222512812311200450800001002005020049200492004920049
802042004815000000064268011610080016100800285006401960200292004820049997699986801282008003820080038200482004811802011009910010080000100000000222512812311200450800001002004920049200502004920049
8020420049150000000642680116100800161008002850064019612002920048200489976109986801282008003820080038200492004811802011009910010080000100000000222512912311200450800001002004920049200492004920049
802042004915000000064268011610080016100800285006401961200292004820048997699986801282008003820080038200492004811802011009910010080000100000000222512812311200460800001002004920049200502005020049
802042004815000000064268011610080016100800285006401960200292004820048997699986801282008003820080038200482004811802011009910010080000100000000222512912311200450800001002005020049200492004920049
80204200481500000001282780116100800161008002850064019612002920048200489976999868012820080038200800382004820048118020110099100100800001000000990222512812311200460800001002005020050200492004920050
802042004915000000064268011610080016100800285006401960200292004920048997699986801282008003820080038200482004811802011009910010080000100000030222512812311200450800001002005020050200492004920049
80204200491500000006427801161008001610080028500640196120029200482004899761099868012820080038200800382004920048118020110099100100800001000000120222512912311200450800001002004920049200502005020049
8020420048150000000642680116100800161008002850064019602002920048200499976109986801282008003820080038200482004811802011009910010080000100000000222512812311200460800001002005020050200502004920049

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)696d6edispatch 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)9fa7a8a9acc2cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500515258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100003050204166320036080000102004020040200402004020040
8002420039150082258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100006050204164320036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000078050204163420036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000018050204163420036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001011472050203164320036080000102004020040200402004020040
80024200391500325258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000050204163420036080000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000120050204164320036080000102004020040200402004020040
8002420039150040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000050203164320036080000102004020040200402004020040
8002420039150040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000050203164320036080000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000171050204164320036080000102004020040200402004020040