Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHRN (8H)

Test 1: uops

Code:

  uqrshrn v0.8b, v0.8h, #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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073216112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshrn v0.8b, v0.8h, #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)030b191e1f3f4e51inst 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)9fa1a6a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225001508229547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018030037300372826432874510100200100002001016730037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722410006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018030037300372826432876310100200100002001000030037300371110201100991001001000010000004708071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030083300371110201100991001001000010000000071011612296330100001003003830038300383003830038
10204300372250200163829547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010002000071011621296330100001003003830038300383003830038
1020430037225044806129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830071300383003830038
1020430037225000045629547251012810410000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4c4e51inst 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
10024300372240000000610295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000610295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000610295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000006740295472510010101000010100005042785121300183003730037282863287671001020100002010000300373003711100211091010100001000320276806402162229629010000103003830038300383003830038
10024300372250000000610295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000610295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000610295472510010101000010100005042771601300183003730037282913287671001020100002010000300373003711100211091010100001000000076402163229629110000103003830133300383013130085
10024300842250000000610295472510010121000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010006402162429629110000103003830038300383003830038
10024300372250000000610295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000610295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqrshrn v0.8b, v8.8h, #3
  uqrshrn v1.8b, v8.8h, #3
  uqrshrn v2.8b, v8.8h, #3
  uqrshrn v3.8b, v8.8h, #3
  uqrshrn v4.8b, v8.8h, #3
  uqrshrn v5.8b, v8.8h, #3
  uqrshrn v6.8b, v8.8h, #3
  uqrshrn v7.8b, v8.8h, #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)03183f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042009215001586280108102800081008013250064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000431115118016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915001772580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001031115118016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010020121115118027020036800001002004020040200402004020040
80204200391501302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001001115118016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915008922580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000822580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020141616152003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020171615132003680000102004020087200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020141615112003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101005020161613162003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010045365020151615152003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020101614142003680000102004020040200402004020040
80024200391500011362580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020131613212003680000102004020040200402004020040
8002420039150005152580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020161616132003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020101616132003680000102004020040200402004020040
8002420039150001242580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020121612152003680000102004020040200402004020040