Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLAH (vector, 4H)

Test 1: uops

Code:

  sqrdmlah v0.4h, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(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)0308090b18191e1f3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
100430372300000001052548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037220000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000090612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037230000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037220000000612548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037220000000612548251000100010003983130301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlah v0.4h, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 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)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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000500000710041622296340100001003003830038300383003830038
10204300372250000240161295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000000710031622296340100001003003830038300383003830038
1020430037225000000082295482510111100100001001000050042773130300180300373003728265328762101002001000020030000300373003711102011009910010010000100000000000710021622296340100001003027530279303753037130373
10204300852281172933616045582948415910144124100561181089462142866211302700303683036828289372887411166222103292263348030371304099110201100991001001000010042010207354008670396422988613100001003037130369304243013330360
10204303702270000128807692948566101681161006411310596599428270303016203032330372282802928854107732201099721832985303243022861102011009910010010000100700020400780021625296340100001003066230424304253037330362
10204303732350061015848800770429467188101801311009612511192664428681203048603065330455283076128906111672461201824030993303693056213110201100991001001000010024200222550007100216232988616100001003047130324304173041930368
1020430369236001089245280279029494123101451131000012010298560427731303023403035730407282943828745108592361216323636744305143045311110201100991001001000010000302251202009791288242999510100001003064930467304203056230038
1020530037225000000061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000000710121622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000000710131622296340100001003003830038300383003830038
1020430037225000030061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3f4e51inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110901010100001000640216222963010000103003830038300383003830038
10024300372240012612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110901010100001000661416222963010000103003830038300853008530038
10024300372251007332954825100101010008101000050427867013001830037300372828732876710010201000020300003003730037111002110901010100001000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110901010100001013640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110901010100001000640216222963010000103003830038300383003830038
10024300372250018612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110901010100001000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101014950427731303001830037300372828732876710010201000020300003003730037211002110901010100001030640216232963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110901010100001000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110901010100001010640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110901010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlah v0.4h, v0.4h, v1.4h
  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)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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007531161129634100001003003830038300383003830038
10204300372250612954825101001181000810010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007561161129634100001003003830038300383003830038
10204300372250842954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372251000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222970210000103003830038300383003830038
10024300372250000612954825100101010000101000050427779703001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830085300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010100640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqrdmlah v0.4h, v1.4h, v0.4h
  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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240021061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250391242953925100101010000101000050427867013001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225001562954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216232963010000103003830038300383003830038
1002430037225005362954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlah v0.4h, v8.4h, v9.4h
  movi v1.16b, 0
  sqrdmlah v1.4h, v8.4h, v9.4h
  movi v2.16b, 0
  sqrdmlah v2.4h, v8.4h, v9.4h
  movi v3.16b, 0
  sqrdmlah v3.4h, v8.4h, v9.4h
  movi v4.16b, 0
  sqrdmlah v4.4h, v8.4h, v9.4h
  movi v5.16b, 0
  sqrdmlah v5.4h, v8.4h, v9.4h
  movi v6.16b, 0
  sqrdmlah v6.4h, v8.4h, v9.4h
  movi v7.16b, 0
  sqrdmlah v7.4h, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042006515001317258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500444258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150362258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100501011111611200611600001002006520065200652006520065
16020420064150639258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064151039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100091011111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010001501011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

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)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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242006515000045258001212800001280000626400000120027200502004632280012208000020240000200502005011160021109101016000010001003532210202119820043215160000102004720047200472004720047
16002420046150110512580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100010036622122642212920047231160000102005320051200532005320053
16002420050150010452580012128000012800006264000001200272005220046322800122080000202404202005720050111600211091010160000100010032311112021191120043215160000102004720047200472004720047
16002420046150000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100010035322122642291120047215160000102004720047200472004720047
16002420046150000452580012118000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100010032311112021191120043215160000102004720047200472004720047
1600242005015000155125800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000100343211220211111020043215160000102004720047200472004720047
16002420050150000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100010031611112041110920043215160000102004720047200472005120051
1600242004615100645258001212800001280000626400001120031200462004632280012208000020240000200462004611160021109101016000010001003231110203119920043215160000102004720047200472005320047
16002420046150000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100010034311102421211920043215160000102004720047200472004720047
160024200461500004525800121280000128000062640000112003320046200463228001220800002024000020046200501116002110910101600001000100333111024212111220043215160000102004720051200472004720053

Test 6: throughput

Count: 16

Code:

  sqrdmlah v0.4h, v16.4h, v17.4h
  sqrdmlah v1.4h, v16.4h, v17.4h
  sqrdmlah v2.4h, v16.4h, v17.4h
  sqrdmlah v3.4h, v16.4h, v17.4h
  sqrdmlah v4.4h, v16.4h, v17.4h
  sqrdmlah v5.4h, v16.4h, v17.4h
  sqrdmlah v6.4h, v16.4h, v17.4h
  sqrdmlah v7.4h, v16.4h, v17.4h
  sqrdmlah v8.4h, v16.4h, v17.4h
  sqrdmlah v9.4h, v16.4h, v17.4h
  sqrdmlah v10.4h, v16.4h, v17.4h
  sqrdmlah v11.4h, v16.4h, v17.4h
  sqrdmlah v12.4h, v16.4h, v17.4h
  sqrdmlah v13.4h, v16.4h, v17.4h
  sqrdmlah v14.4h, v16.4h, v17.4h
  sqrdmlah v15.4h, v16.4h, v17.4h
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030818191e1f373f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400593000000004102516010010016000010016000050024388651400204003940039199733199981601002001600002004800004003940039111602011009910010016000010000010601011021611400361600001004004040040400404004040040
160204400392990000004102516010010016000010016000050012800001400204003940040199733199971601002001600002004800004003940039111602011009910010016000010000000001011011611400451600001004004040040400404004040040
160204400393000000004102516010010016000010016000050024388651400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000001011011611400361600001004004040040400404004940040
1602044003930000000070602516010010016000010016000050012800001400214003940039199733199971601002001600002004800004003940040111602011009910010016000010000000001011011611400361600001004004040040400404004040040
160204400393000000004102516010010016000010016000050024388651400204003940039199733200091601002001600002004800004003940039111602011009910010016000010000000001011011611400361600001004004040040400404004040040
160204400393000000004102516010010016000010016000050012800001400214004940049199733199971601002001600002004800004003940039411602011009910010016000010000000001011011611400361600001004005040040400404004040040
16020440039300000000410251601181001600181001600005001280000140020400394003919973319997160100200160000200480000400394003931160201100991001001600001000000024001011011611400361600001004027840049400404004940040
16020440040300000000410251601001001600001001600005001280000140020400394004019973319997160100200160000200480000400394003911160201100991001001600001000000015901011041611400361600001004004040040401584005040040
160204400393000000004102516010010016000010016010550012800001400204003940039199733200071601002001600002004800004003940040111602011009910010016000010002000001016811611401191600001004004040040400404004040040
1602044004030010000185102516010010016000010016000062024388650400204004940049199733199971601002001600002004800004004040039111602011009910010016000010000000001013411611400361600001004004040040400404004040040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2504

retire (01)cycle (02)03070a1e373a3f51inst 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)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)9fa1a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024401143001000158251600101016000010160000502398999114002040039400391999603200281600102016000020480000400394003911160021109101016000010000001002231145161112738400360165160000104004040040400404004040040
16002440069300100004625160010101600001016000050128000011400204003940039199960320019160010201600002048000040039400391116002110910101600001000022801002231136161113821400460165160000104004040040400404004040040
160024400643001100146251600101016000010160000501280000114002040039400391999603200191600102016000020480000400394003911160021109101016000010000001002231138161112540400360165160000104004040040400404004040040
1600244007029911017046251600101016001710160000501280000214002040039400391999603200191600102016000020480000400394003911160021109101016000010010301002231138161113924400360165160000104004040040400404004040040
16002440067300100005825160010101600001016000050128000021400204003940049199960320019160010201600002048000040039400391116002110910101600001000026101002331137161114024400360165160000104004040040400404004040040
160024400643001100046251600101016001810160000502398999214003040039400391999603200191600102016000020480000400484003911160021109101016000010000001002331139161112640400360165160000104004040040400404004040040
16002440064300110180723521600101016000010160000501280000114002040039400391999603200191600102016000020480000400484003911160021109101016000010000001002331122161113740400360166160000104005040040400404005040040
1600244006430000017058251600101016000010160000501280000114002040039400391999603200191600102016000020480000400394003911160021109101016000010000001002331131161114039400450165160000104004040040400404004040049
1600244007030010001462516001010160000101600005012800001140020400394003919996032002816001020160000204800004003940039111600211091010160000100008101002231136161112639400360165160000104004940049400404004040040
160024400793001000058251600101016000010160000501280000214002040039400391999603200191600102016000020480000400394003911160021109101016000010000001002331126161113939400360165160000104004040050400404004040040