Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHRN (8H)

Test 1: uops

Code:

  uqshrn 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)a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723126125472510001000100039816013018303730372414328951000100010003037303711100110000020073216222629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000010073216222629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000270073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000022845073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000270073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000003073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000033073216222629100030383038303830383038
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqshrn 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)03091e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954725101251251000012510000500427716030018300373003728264328800102762001000020010000300373003711102011009910010010000100000710316112963325100001003003830038300383003830038
102043003722504561295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010010071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372826432874510430200101652001033030132300371110201100991001001000010010073211611296330100001003003830038300383003830038
1020430037225045103295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722501261295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722502161295292510100100100001001000050042771603001830037300372826432874410100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000062642771603001830037300372826432874510100200100002001000030037300371110201100991001001000010003071011611296330100001003003830038300383003830038
102043003722503061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225021612954725101251081000012510000626427716030018300373003728268328763101002001000020010000300373003711102011009910010010000100000710116112963325100001003003830038300383003830038
102043003722503961295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9fa6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037260006021229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403162229629010000103003830038300383003830038
10024300372600006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372600008229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402172229629010000103003830038300383003830038
10024300372410006129547251001010100001010000504277160030018300373003728286328823100102010000201000030037300371110021109101010000103050006402162229629010000103003830038300383003830038
10024300372420006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372410008229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100012283626612242229629010000103003830038300383003830038
10024300372411106129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003723200072629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629110000103003830038300383003830038
10024300372290006129547251001010100001010000504277160030018300373003728286328767100102010000201065030037300371110021109101010000100000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqshrn v0.8b, v8.8h, #3
  uqshrn v1.8b, v8.8h, #3
  uqshrn v2.8b, v8.8h, #3
  uqshrn v3.8b, v8.8h, #3
  uqshrn v4.8b, v8.8h, #3
  uqshrn v5.8b, v8.8h, #3
  uqshrn v6.8b, v8.8h, #3
  uqshrn 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): 0.2506

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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915105125801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100015611151180160020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000311151180160020036800001002004020040200402004020040
8020420039150045258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010006911151180160020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010001511151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100016511151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100014411151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100021911151180160020036800001002004020040200402004020040
8020420039150030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e3f51inst 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)9fa8accfd0d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001516013152003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001416011152003680000102004020040200402004020040
80024200391620004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001316012122003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001416013142003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001516015162003680000102004020040200402004020040
800242003915000154025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001216012152003680000102004020040200402004020040
80024200391500064025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001216014142003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001316013162003680000102004020040200402004020040
80024200391500007052580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050200141609142003680000102004020040200402004020040
800242003915600544025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502001316014122003680000102004020040200402004020040