Apple M1 Microarchitecture Research by Dougall Johnson

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

SUQADD (scalar, B)

Test 1: uops

Code:

  suqadd b0, b1
  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
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372308425482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372208425482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830843038
1004303723010325482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303722046225482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000373216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216232630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303722016825482510001000100039831303018303730372415328951000100020003037303711100110000073216232630100030383038303830383038

Test 2: Latency 1->1

Code:

  suqadd b0, b1
  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)030818191e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010410000500427731313001830037300842826532874510100200100002002000030037300371110202100991001001000010000071011611296340100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000710116122970410100001003012130085300853008530086
10204300372251111741166312954825101001001000010010000500427867003005430085301322826532874510100200100002002000030037300371110201100991001001000010002371011611296340100001003003830038300383003830038
1020430037225000006312954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

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)72scheduler 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
100243003722500000002752954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000006402162329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000006402162329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828773287671001020100002020000300373003711100211091010100001000100006402162329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006402162329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300702828703287671001020100002020000300373003711100211091010100001000000006402162329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000010006402162329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000006402162329630010000103003830071300383003830133
10024300372250000000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000306402163329630010000103003830038300383003830038
100243003722500003000612954825100101010008111000050427867013005430037300372828703287671001020100002020000300373003711100211091010100001000000280306402162329630010000103003830086300383003830038

Test 3: Latency 1->2

Code:

  suqadd b0, b0
  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)030818191e1f3a3f4e51inst 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)9fa1a7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000612954725101001001000010010150500427716030018300373003728271628740101002001000820020000300373003711102011009910010010000100000011171721600296460100001003003830038300383003830038
1020430037225000000612954725101001001000010010000500427716030018300373003728271628740101002001000820020016300373003711102011009910010010000100000011171701603296460100001003003830038300383003830038
1020430037224000000612954725101001021001610010000500427716030018300373003728252628733101002001000021420000300373003711102011009910010010000100000011172222432296290100001003003830038300383003830038
102043003722500002641972954725101001001000010010000500427716030018300373003728252628733101002001000020020000300373022811102011009910010010000100000011172222422296290100001003003830038300383003830038
1020430037225000001972954725101001001000010010000500427716030018300373003728252628733101002001000020020000300373003711102011009910010010000100000011172222422296290100001003003830038300383003830038
1020430037225000001972954725101001001000010010000500427716030018300373003728252628733101002001000020020000300373003711102011009910010010000100200011172222422296290100001003003830038300853008530085
1020430037225012001972953825101001001000010010000500427716030018300373003728252628733101002001000020020000300373003711102011009910010010000100000011172222422296290100001003003830038300383003830038
102043003722500000127262954725101001001000010010000500427716030018300373003728256628733101002001000020020000300373003711102011009910010010000100000011172222422296290100001003003830038300383003830086
1020430037225000001972954725101001001000010010000500427716030018300373003728252628733101002001000020020000300373003711102011009910010010000100021011172222422296290100001003003830038300383003830038
1020430037225000001972954725101001001000010010000500427716030018300373003728252628733101002001000020020000300373003711102011009910010010000100000011172222422296290100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e1f3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000294295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295382510042101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000006402162229629110000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001022100002020000300373003711100211091010100001000006402162229629010000103003830038300383003830038
100243003722510012061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000006402162229629010000103003830038300383003830038
100243003722500000726295472510010101000010100005042771600300183003730037282863287671001020106602020000300373003711100211091010100001000006402162429629010000103003830038300383003830038
100243022522500000124295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001003206402162229629010000103003830038300853017730038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000006403492229629010000103003830038300383003830038
10024300372250100061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024302272250000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001001006402162229629010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  suqadd b0, b8
  movi v1.16b, 0
  suqadd b1, b8
  movi v2.16b, 0
  suqadd b2, b8
  movi v3.16b, 0
  suqadd b3, b8
  movi v4.16b, 0
  suqadd b4, b8
  movi v5.16b, 0
  suqadd b5, b8
  movi v6.16b, 0
  suqadd b6, b8
  movi v7.16b, 0
  suqadd b7, b8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200881500000150169258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119216002006201600001002006620066200662006620066
1602042006515000000029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119216002006201600001002006620066200662006620066
1602042006515000000029258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119216002006201600001002006620066200662006620066
16020420065150000000314258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119216002006201600001002006620066200662006620066
1602042006515000000029258011610080016100800285006401961200452016820226612801282008002820016005620065200651116020110099100100160000100000000011110119116002006201600001002006620066200662006620066
1602042006515100000029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119116002006201600001002006620066200662006620066
1602042006515000000029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119116002006201600001002006620066200662006620066
1602042006515000000029258011610080016100800285006401961200452006520065651801282008002820016005620065200651116020110099100100160000100000000011110119117002006201600001002006620066200662006620066
1602042006515000000029258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119116012006201600001002006620066200662006620066
1602042006515000000052258011610080016100800285006401960200452006520065612801282008002820016005620065200651116020110099100100160000100000000011110119216002006201600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307090a0b1e3a3f51inst 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)5f60696d6escheduler 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)9faccfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007215000100057258001010800001080000506400001120027200462004632280010208000020160000200462005411160021109101016000010010043622422724318172004330160000102004720047200472005120047
1600242005015010100051258001010800001080000506400001120027200462004632280010208000020160000200462004611160021109101016000010010037311322721113192004315160000102005120051200512005120051
1600242005015000100068258001010800001080000506400001120027200462004632280010208000020160000200462005011160021109101016000010010043311322922220192004330160000102004720047200472004720047
16002420046150102090419258001010800001080000506400001120027200462004632280010208000020160000200502005011160021109101016000010010042311272721120202004315160000102004720047200472004720047
1600242004615010100057258001010800001080000506400001120091200462004632280010208000020160000200462004611160021109101016000010010041311212721118212004315160000102004720047200472004720047
1600242004615010100087258001010800001080000506400001120027200462004632280010208000020160000200462004611160021109101016000010010042311313721118192004315160000102004720047200472004720047
1600242004615010100045258001010800001080000506400001120027200462004632280010208000020160000200462005011160021109101016000010010046622373342218172004730160000102005120051200512004720047
1600242005015020100063258001010800001080000506400001120031200502005032280010208000020160000200502004611160021109101016000010010044622273542317132004730160000102005120051200472004720047
1600242004615010000084258001010800001080000506400000120031200502005034480010208000020160000200502005011160021109101016000010010045622193542218172004730160000102005120051200512005120051
16002420050150301000925258001010800001080000506400000120031200502005032280010208000020160000200502005011160021109101016000010010043622283642216182004730160000102005120047200512005120051

Test 5: throughput

Count: 16

Code:

  suqadd b0, b16
  suqadd b1, b16
  suqadd b2, b16
  suqadd b3, b16
  suqadd b4, b16
  suqadd b5, b16
  suqadd b6, b16
  suqadd b7, b16
  suqadd b8, b16
  suqadd b9, b16
  suqadd b10, b16
  suqadd b11, b16
  suqadd b12, b16
  suqadd b13, b16
  suqadd b14, b16
  suqadd b15, b16
  movi v16.16b, 17

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03191e3a3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440049300000302516010810016000810016002050012801320400204003940039199776199901601202001600322003200644003940039111602011009910010016000010020011110118016400361600001004004040040400404004040040
1602044003930000030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
1602044003930000030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
1602044003930000030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
16020440039299000179251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
1602044003930000030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
1602044003929900030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
1602044003930000030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
1602044003930000030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000011110118016400361600001004004040040400404004040040
1602044003930000074251601081001600081001600205061280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001008011110118016400361600001004004040040400404004040040

1000 unrolls and 10 iterations

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

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)5f6061696b6d6edispatch 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)9fa6a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244005129904625160010101600001016000050128000011040020040039400391999632001916001020160000203200004003940039111600211091010160000100000100223219162114640036155160000104004040040400404004040040
16002440039300087251600101016000010160000501280000100400200400394003919996320019160010201600002032000040039400391116002110910101600001000001002231112162116440036155160000104004040040400404004040040
160024400393000462516001010160000101600005012800001004002004003940039199963200191600102016000020320000400394003911160021109101016000010000010022321516211101240036155160000104004040040400404004040040
1600244003930004625160010101600001016000050128000011040020040039400391999632001916001020160000203200004003940039111600211091010160000100000100223219162114640036155160000104004040040400404004040040
16002440039300046251600101016000010160000501280000100400200400394003919996320019160010201600002032000040039400391116002110910101600001000001002232161621141040036155160000104004040040400404004040040
160024400393000462516001010160000101600005012800001104002004003940039199963200191600102016000020320000400394003911160021109101016000010000010022311121621141040036155160000104004040040400404004040040
160024400393000462516001010160000101600005012800000104002004003940039199963200191600102016000020320000400394003911160021109101016000010000010022312101621176400361518160000104004040040400404004040040
16002440039300046251600101016000010160000501280000100400200400394003919996320019160222201600002032000040039400391116002110910101600001000001002231161621110440036155160000104004040040400404004040040
1600244003930004625160010101600001016000050128000011040020040039400391999632001916001020160000203200004003940039111600211091010160000100000100223218164214640036155160000104004040040400404004040040
160024400392990522516001010160000101600005012800001004002004003940039199963200191600102016000020320000400394003911160021109101016000010000010022311101621110540036155160000104004040040400404004040040