Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHRN2 (2D)

Test 1: uops

Code:

  uqrshrn2 v0.4s, v1.2d, #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)031e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
1004303723006125482510001000100039831330223037303724153289510001000200030373037111001100000073316112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037221206125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037221206125482510001000114939831330183037303724153289510001000200030373037111001100001073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000200030373037111001100000094116112630100030383038303830383038
1004303722006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289511491000200030373037111001100000073116112630100030383038303830383038
1004303722006125482510001000100039831330183037303724153289510001000200030373037111001100000275573116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  uqrshrn2 v0.4s, v1.2d, #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)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)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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000008642954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000300071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000001702954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000001282953944101251001000812810000500428002713001830037300372826532874510100200100002022000030037300371110201100991001001000010000002303071011611297010100001003008630038300863012330038
1020430037225000000126295392510100100100001001000050042773131300183003730037282653287451010020010000200203343003730037111020110099100100100001000000019470865373232990232100001003037130372303713032430323
102043036922711779246165666294851651019714810056139104477394286775130270300853037128290362887210254222113302262263830371301808110201100991001001000010020200251358692105122998032100001003046530467304683042230323
10204304192281192118870452092947618210222143100641451134169542880171303063046830467283054628892114282161132222722988304663045610110201100991001001000010000010071011611296340100001003003830038300383003830038
10204300372240000001072954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510228200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006403242229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020322300853008511100211091010100001000006402162229630010000103003830038300383003830038
10024300372250000536295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830180
1002430037224000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000084295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225006061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  uqrshrn2 v0.4s, v0.2d, #3
  movi v0.16b, 1

(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)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)cdcfd6e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129547251010010010000100100005004277160300183003730037282716287411010020010008200200163003730037111020110099100100100001000011171816296450100001003003830038300383003830038
1020430037225087429547251010010010000100100005004277160300183003730037282717287401010020010008200200163003730037111020110099100100100001000011171716296450100001003003830038300383003830038
1020430037225012629547251010010010000100100005004277160300183003730037282717287401010020010008200200163003730037111020110099100100100001000011171716296460100001003003830038300383003830038
1020430037225126129547251010010010000100100005224277160300903008430037282757287411010020010008200200163003730037111020110099100100100001001287311171816296460100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282716287401010020010008200200163003730037111020110099100100100001000011171816296450100001003003830038300383003830038
1020430037225010329547251010010010000100100005004277160300183003730037282716287401010020010008200200163003730037111020110099100100100001000011171716296452100001003003830038300383003830038
1020430037225128229547251010010010000100100005004277160300183003730037282717287401010020010008200200163003730037111020110099100100100001000011171716296450100001003003830038300383003830038
102043003722508229547251010010010000100100005004277160300183003730037282717287401010020010008200200163003730037111020110099100100100001002011171716296450100001003003830038300383003830038
10204300372241293529547251010010010000100100005004277160300183003730037282717287401010020010008200200163003730037111020110099100100100001000011171816296450100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282716287411010020010008200200163003730037111020110099100100100001000011171816296460100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500200295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002020324300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722500103295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722500170295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722500145295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000640216222962910000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  uqrshrn2 v0.4s, v8.2d, #3
  movi v1.16b, 0
  uqrshrn2 v1.4s, v8.2d, #3
  movi v2.16b, 0
  uqrshrn2 v2.4s, v8.2d, #3
  movi v3.16b, 0
  uqrshrn2 v3.4s, v8.2d, #3
  movi v4.16b, 0
  uqrshrn2 v4.4s, v8.2d, #3
  movi v5.16b, 0
  uqrshrn2 v5.4s, v8.2d, #3
  movi v6.16b, 0
  uqrshrn2 v6.4s, v8.2d, #3
  movi v7.16b, 0
  uqrshrn2 v7.4s, v8.2d, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2509

retire (01)cycle (02)0304080b18191e1f3f51inst 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)60696d6escheduler 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)9fa6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420090150000000050258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000029258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000029258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000029258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000052258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
160204200651500000000694258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150000000029258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03090b18191e3a3f51inst 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)5f6061696d6escheduler 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)9fa7a8a9acbranch mispredict (cb)cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200651500000004525800101080000108000050640000115200272004620046322800102080000201600002004620046111600211091010160000100000001003282192021110920043150160000102004720047200472004720047
1600242004615000000045258001010800001080000506400001152002720046200463228001020800002016000020046200461116002110910101600001000000010031821112021191120043150160000102004720047200472004720047
16002420046150000000452580010108000010800005064000011520027200462004632280010208000020160000200462004611160021109101016000010000000100338211020211111120043150160000102004720047200472004720047
160024200461500000008725800101080000108000050640000115200272004620046322800102080106201600002004620046111600211091010160000100120001003282192021191120043150160000102004720047200472004720047
1600242004615000000073258001010800001080000506400001152002720046200463228001020800002016000020046200461116002110910101600001000000010034821122021110920043150160000102004720047200472004720047
1600242004615000000045258001010800001080000506400001152002720046200463228001020800002016000020046200461116002110910101600001000000010032821920211101120043150160000102004720047200472004720047
16002420046150000000662580010108000010800005064000011520027200462004632280010208000020160000200462004611160021109101016000010000000100348219202119820043150160000102004720047200472004720047
16002420046150000000452580010108000010800005064000011520027200462004632280010208000020160000200462004611160021109101016000010000000100348211220211111120043150160000102004720047200472004720047
16002420046150000000452580010108000010800005064000011520027200462004632280010208000020160000200462004611160021109101016000010000000100338211020211111020043150160000102004720047200472004720047
160024200461500000004525800101080000108000050640000115200272004620046322800102080000201600002004620046111600211091010160000100000001003382192021111920043150160000102004720047200472004720047

Test 5: throughput

Count: 16

Code:

  uqrshrn2 v0.4s, v16.2d, #3
  uqrshrn2 v1.4s, v16.2d, #3
  uqrshrn2 v2.4s, v16.2d, #3
  uqrshrn2 v3.4s, v16.2d, #3
  uqrshrn2 v4.4s, v16.2d, #3
  uqrshrn2 v5.4s, v16.2d, #3
  uqrshrn2 v6.4s, v16.2d, #3
  uqrshrn2 v7.4s, v16.2d, #3
  uqrshrn2 v8.4s, v16.2d, #3
  uqrshrn2 v9.4s, v16.2d, #3
  uqrshrn2 v10.4s, v16.2d, #3
  uqrshrn2 v11.4s, v16.2d, #3
  uqrshrn2 v12.4s, v16.2d, #3
  uqrshrn2 v13.4s, v16.2d, #3
  uqrshrn2 v14.4s, v16.2d, #3
  uqrshrn2 v15.4s, v16.2d, #3
  movi v16.16b, 17

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)0318191e3f51inst 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)9fa1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440059300000179261601161001600161001600285001280196040029400494004819976101998616012820016003820032007640049400491116020110099100100160000100000002221012922311400461600001004005040049400494004940050
160204400493000006427160116100160016100160028500128019604002940048401211997691998616012820016003820032007640049400491116020110099100100160000100000002221012812311400451600001004005040050400504004940049
160204400493000006426160116100160016100160028500128019604002940048400481997691998616012820016003820032007640048400491116020110099100100160000100000002221012912311400451600001004004940050400494004940049
16020440048300000642716011610016001610016002850012801960400294004940048199769200141603312001601432003200764004840098111602011009910010016000010023029402221012812311400451600001004051140677405154062440257
1602044004930011041826160406100160016100160028500128019614002940049400491997691998616012820016014320032007640048400481116020110099100100160000100000002221012812311400451600001004005040050400504004940050
160204400483000006427160116100160016100160028500128019614002940049400481997691998616012820016003820032007640048400481116020110099100100160000100000002221012812311400451600001004004940049400494004940050
160204400483000006426160116100160016100160028500128019604002940113400481997691998616012820016003820032007640048400481116020110099100100160000100000002221012812311400451600001004004940049400494005040049
1602044004830000064261601161001600161001600285001280196140029400494004819976919986160128200160038200320076400484004811160201100991001001600001000000332221012812311400461600001004004940049400504005040049
160204400483000006426160116100160016100160028500128019614002940048400481997691998616012820016003820032007640048400491116020110099100100160000100000002221012912311400451600001004004940049400494004940049
1602044004830000064451602131001600161001600285001280196040070401514004819976141998616012820016003820032007640048400491116020110099100100160000100000002221016212321400881600001004004940049400494005040050

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)030408090b18191e1f3a3f51inst 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)5f6061696d6edispatch 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)9fa0a8branch mispredict (cb)cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244005130010000012011692516001010160000101600005012800001154002040039400391999632001916001020160000203200004003940040111600211091010160000100001002480104116111172940036165160000104004040040400404004040040
160024401423001010001200992516001010160000101600005012800001154002040039400391999632001916001020160000203200004003940039111600211091010160000100001002284106016111222740036165160000104004040040400404004040040
16002440039300101000000992516001010160000101600005012800001154002040039400391999632001916001020160000203200004003940039111600211091010160000100001002484111616311192940036165160000104004040040400404004040151
1600244015130010112226417614946516020510160195101602125012816201154002040039400391999632001916001020160000203200004003940039111600211091010160000100001002484113016311293040036165160000104004040040400404004040040
160024400393001010000007582516001010160000101600005012800001154002040039400391999632001916003420160000203200004003940039111600211091010160000100101002384112516311242440036165160000104004040040400404004040040
160024400393001010000009325160010101600001016000050128000001540020400394003919996320019160010201600002032000040099400391116002110910101600001000010026115112016311282440036165160000104004040040400404004040040
1600244003930010100000193251600101016000010160000501280000115400204003940039199963200191600102016000020320000400394003911160021109101016000010000100231151126163112525400361610160000104004040040400404004040040
160024400393001010001201992516001010160000101600005012800001154002040039400391999632001916001020160000203200004003940039111600211091010160000100001002384112616122262540036315160000104004040040400404004040040
16002440039300101000000932516001010160000101600005012800001154002040039400391999632001916001020160000203200004003940039111600211091010160000100001002485112716321252840036165160000104004040040400404004040040
16002440039300101000001932516001010160000101600005012800001154002040039400391999632001916001020160000203200004003940039111600211091010160000100001002385112716111262640118165160000104004040040400404004040040