Apple M1 Microarchitecture Research by Dougall Johnson

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

SRSRA (vector, D)

Test 1: uops

Code:

  srsra d0, d1, #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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037229612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110001573116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372302512548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  srsra d0, d1, #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)030b3f4e51inst 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
10204300372240612954825101001001000010010000500427731313001830037300372826532876210274200100002002000030037300371110201100991001001000010000337101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000217101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000937101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100001387101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000997101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372828732874510100200100002002000030037300371110201100991001001000010000697101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100001147101161129634100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100002107101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100001207101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000127101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3a3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001001890640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001001350640216222963010000103003830038300383008430038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225120061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225120061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010004661216222963010000103003830038300383003830038
100243003722501920783295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000103295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010100640216222963010000103003830038300383003830038
1002430037225000103295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010090640216222963010000103003830038300383003830038
100243003722500061295482510010101000810100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  srsra d0, d0, #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)03181e3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400612954725101001001000010010000500427716003001803003730037282717287401010020010008200200163003730037111020110099100100100001005031117171629646100001003003830038300383003830038
102043003722400612954725101001001000010010000500427716003001803003730037282716287411010020010008200200163003730037111020110099100100100001003201117171629646100001003003830038300383003830038
1020430037226006129547251010010010000100100005004277160030054330037300372827172874110100200100082002001630037300371110201100991001001000010033991117181629646100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300180300373003728271728741101002001000820020016300373003711102011009910010010000100031117171629645100001003003830038300383003830038
1020430037225063612954725101001001000010010000500427716013001803003730037282717287401010020010008200200163003730037111020110099100100100001005301117171629646100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282717287411010020010008200200163003730037111020110099100100100001003501117181629646100001003003830038300383003830038
10204300372250011412954725101001001000010010000500427716013001803003730037282717287411010020010008200200163003730037111020110099100100100001004401117181629645100001003003830038300383003830038
102043003722600612954725101001001000010010000500427716013001803003730037282716287401010020010008200200163003730037111020110099100100100001004431117181629646100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282717287401010020010008200200163003730037111020110099100100100001003031117181629646100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282716287401010020010008200200163003730037111020110099100100100001004101117181629646100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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
1002430037225612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010383640216222962910000103003830038300383003830038
1002430037227612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010336640216222962910000103003830038300383003830038
1002430037225612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010413640216222962910000103003830038300383003830038
1002430037225612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010360640216222962910000103003830038300383003830038
1002430037224612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010350640216222962910000103003830038300383003830038
1002430037225612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010021640216222962910000103003830038300383003830038
1002430037225612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010443640216222962910000103003830038300383003830038
1002430037225612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010453640216222962910000103003830038300383003830038
1002430037225612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010473640216222962910000103003830038300383003830038
1002430037225612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010450640216222962910000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  srsra d0, d8, #3
  movi v1.16b, 0
  srsra d1, d8, #3
  movi v2.16b, 0
  srsra d2, d8, #3
  movi v3.16b, 0
  srsra d3, d8, #3
  movi v4.16b, 0
  srsra d4, d8, #3
  movi v5.16b, 0
  srsra d5, d8, #3
  movi v6.16b, 0
  srsra d6, d8, #3
  movi v7.16b, 0
  srsra d7, d8, #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)03080b1e3f51inst 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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200901510002925801161008001610080028500640196120045200652006561280128200800282001600562006520065111602011009910010016000010000001111011901600200621600001002006620066200662006620066
160204200651500002925801161008001610080028500640196120045200652006561280128200800282001600562006520065111602011009910010016000010000001111011901600200621600001002006620066200662006620066
160204200651500002925801161008001610080028500640196120045200652006561280128200800282001600562006520065111602011009910010016000010000001111011901600200621600001002006620066200662006620066
160204200651500002925801161008001610080028500640196120045200652006561280128200800282001600562006520065111602011009910010016000010002091111011901600200621600001002006620066200662006620066
1602042006515100029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000241111011901611200741600001002007920078200782007820079
1602042007715000065308011910080019100800315006402200200562007720078101280131200800312001600622007720078111602011009910010016000010000002221013112311200741600001002007820078200782007820078
160204200771500006529801191008001910080031500640220020056200782007791280131200800312001600622007720077111602011009910010016000010000002221013112311200741600001002007820078200792007820078
1602042007715000065308011910080019100800315006402201200562007720078101280131200800312001600622007720077111602011009910010016000010000002221013112311200741600001002007920079200782007920079
160204200771500006530801191008001910080031500640220020056200772007891280131200800312001600622007720078111602011009910010016000010000032221013012311200751600001002007820078200782007820078
1602042007815000396529801191008001910080031500640220020056200772007891280131200800312001600622007720078111602011009910010016000010000002221013012311200751600001002007820078200782007920079

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0309181e3f51inst 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)9fa8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200771500012710278001010800001080000506400001102003220051200513228001020800002016000020051200511116002110910101600001000010038112211252119520048201160000102005220052200522005220065
160024200601500005129800101080000108000050640000110200322005120051322800102080000201600002005120051111600211091010160000100001003634163421114920048201160000102005220052200522006120074
160024200511500004527801151080000108000050640832100200322005120051112280010208010520160000200602005111160021109101016000010660100328415252116920048201160000102006120061200522005220065
160024200511510104527800101080000108000050640000115200322005120051322800102080000201600002005120051111600211091010160000100001003385210252227920048402160000102005220052200522005220065
16002420051150000452780010108000010800005064000011520032200512005132280010208000020160000200512005111160021109101016000010000100338416252118920048201160000102005220052200522005220065
160024200511500005127800101080000108000050640000115200322005120051322800102080000201600002005120060111600211091010160000100001002784172521110520048201160000102005220052200522005220065
1600242005115000045278001010800001080000506400001152003220051200513228001020800002016000020051200511116002110910101600001050010031841525211101420048201160000102005220052200522005220065
1600242005115000087278001010800001080000506400001152003220051200513228001020800002016000020051200511116002110910101600001000010038842925211131320048201160000102005220052200522005220065
1600242005115000045278001010800001080000506400001152003220051200513228001020800002016000020051200511116002110910101600001000010037114114252118520048201160000102005220052200522005220065
1600242005115000124527800101080000108000050640000115200322005120051322800102080000201600002005120051111600211091010160000100001002985172522151120048201160000102006120052200612005220065

Test 5: throughput

Count: 16

Code:

  srsra d0, d16, #3
  srsra d1, d16, #3
  srsra d2, d16, #3
  srsra d3, d16, #3
  srsra d4, d16, #3
  srsra d5, d16, #3
  srsra d6, d16, #3
  srsra d7, d16, #3
  srsra d8, d16, #3
  srsra d9, d16, #3
  srsra d10, d16, #3
  srsra d11, d16, #3
  srsra d12, d16, #3
  srsra d13, d16, #3
  srsra d14, d16, #3
  srsra d15, d16, #3
  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)03070a0b181e3f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044005930011000302516010810016000810016002050012801321400204003940039199776199901601202001600322003200644003940039111602011009910010016000010001031111011811611400361600001004004040040400404004040040
1602044003930011000304916010810016000810016002050012801321400204003940039199776199901601202001600322003200644003940039111602011009910010016000010002991111011811611400361600001004004040040400404004040040
1602044003930011000302516010810016000810016002050012801321400204003940039199776199901601202001600322003200644003940039111602011009910010016000010002861111011811611400361600001004004040040400404004040040
16020440039300110003025160108100160008100160020500128013214002040039400391997761999016012020016003220032006440039400391116020110099100100160000100030121111011811611400361600001004004040040400404004040040
1602044003930011000302516010810016000810016002050012801321400204003940039199776199901601202001600322003200644003940039111602011009910010016000010003201111011811611400361600001004004040040400404004040040
160204400393001100030251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001000861111011811611400361600001004004040040400404004040040
160204400393001100030251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001000301111011811611400361600001004004040040400404004040040
1602044003930011000201251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001000201111011811611400361600001004004040040400404004040040
160204400393001100030251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001004331111011811611400361600001004004040040400404004040040
1602044003930011000302516010810016000810016002050012801321400204003940039199776199901601202001600322003200644003940039111602011009910010016000010003031111011811611400361600001004004040040400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e3f51inst 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)5f60696d6edispatch 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)9fa1a6a8a9acc2cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440050300000000462516001010160000101600005012800000140020400394003919996320019160010201600002032000040039400391116002110910101600001000290300100223224162215540036155160000104097040196400404008040040
1600244003932400000052251600101016000010160000501280000014002040191403001999632001916001020160000203200004003940039111600211091010160000100090000100223125162224540036155160000104004040040400404006440040
16002440039300000000462516001010160000101600005012800000140020400394003919996320019160010201600002032000040039400391116002110910101600001000003001002462241642244400361510160000104004040090400904006740040
16002440039300000000522516001010160000101600005012800000140020400394003919996320019160010201600002032000040039400391116002110910101600001020360000100226224162224440036305160000104004040040400404006440040
16002440039300000000522516001010160000101600005012800000140020400394003919996320019160010201600002032000040039400391116002110910101600001000680000100246214164225540036305160000104004040040400404006440040
16002440039300000000839251600101016000010160104501280000114002040039400391999672001916001020160000203200004003940039111600211091010160000100010015001002462281642247400361510160000104004040040400404006040040
16002440039299000040521711601071016000010160000501280776014002040039401951999632001916011420160000203200004003940039111600211091010160000100070600100223115162115540036155160000104004040040400404006440040
16002440039300000000462516001010160000101600005012800001140020400394003919996182001916001020160000203200004003940039111600211091010160000100060300100223114162115540036155160000104004040040400404006340107
1600244003930010000051925160010101600001016000050128000001400204066440039199963200191600102016031020320208400394003911160021109101016000010002200001002462251642258400363010160000104004040040400404006640040
16002440039300000003946251600101016000010160000501280000114002040039400391999632001916001020160000203200004003940039111600211091010160000100020000100223114162115540036155160000104004040040400404005940040