Apple M1 Microarchitecture Research by Dougall Johnson

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

UMLSL (by element, 2D)

Test 1: uops

Code:

  umlsl v0.2d, v1.2s, v2.s[1]
  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)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
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110006373116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532900100010003000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100030003037303711100110001273116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  umlsl v0.2d, v1.2s, v2.s[1]
  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)031e3a3f4e5051inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954802510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001001715710121622296340100001003003830038300383003830038
102043003722500612954802510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000180710121623296340100001003003830038300383003830038
102043003722500612954802510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000120710121623296340100001003003830038300383003830038
102043003722501612954802510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000147710121622296340100001003003830038300383003830038
1020430037225006129548025101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010003710121622296340100001003003830038300383003830038
102043003722500612954802510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000105710121622296340100001003003830038300383003830038
102043003722500612954802510100100100001001046450042773130300183008430132282653287451010020010000200300003003730037111020110099100100100001000111710121623296340100001003003830038300383003830038
1020430037225006129548025101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010003710121622296340100001003003830038300383003830038
10204300372250061295480251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100099710121622296340100001003003830038300383003830038
102043003722400612954802510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000168710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240061295482510010101000010100005042813840300183003730037282873287671001020100002030000300373003711100211091010100001000210640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001180640216222963010000103003830038300383003830038
100243003723300355295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000390640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010001170640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042786700300183003730037282873287671001020100002030000300373003711100211091010100001000270640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000330640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000210640216232963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010001110640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010001260640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  umlsl v0.2d, v0.2s, v1.s[1]
  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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500300612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010036007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010052007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010052007101161129634100001003003830038300383003830038
10204300372250000612954825101001001002410010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010059007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000037101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000067101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010041007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010038007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100321001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001003007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010039007101161129634100001003003830038300383003830038

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)9fa6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723201214529548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100200016403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100300006403163329630010000103003830038300383003830038
1002430037225006129548251001013100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100403006403163329630010000103003830038300383003830038
1002430037225003717295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001003800006403163329630010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100303006403163329630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001004900006403163329630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001003900006403163329630010000103003830038300383003830038
10024300372250061295482510010121000011100005042773131300183003730037282873287671001020100002030000300373003721100211091010100001003100006403163329630010000103003830038300383003830038
100243003722500279829548251001010100001010000504277313130018300373003728287328786100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001003200006403163329630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  umlsl v0.2d, v1.2s, v0.s[1]
  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)03081e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250060792954844101341001000011910000500427731313001803003730037282653287451010020010000200300003003730037211020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427779713001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250035892954886101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001002007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001001007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a181e3a3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722511002682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000644121610102963010000103003830038300383003830038
100243003722511002682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010010644101610102963010000103003830038300383003830038
1002430037225110026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100106445161082963010000103003830038300383003830038
100243003722511002682954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010010644101610102963010000103003830038300383003830038
1002430037225110026829548251001010100001310000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100106441016952963010000103003830038300383003830038
10024300372251100268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001002064471610102963010000103003830038300383003830038
100243003722511002682954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010010644101610102963010000103003830038300383003830038
100243003722511002682954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010010644101610102963010000103003830038300383003830038
100243003722511002892954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010010644101610102963010000103003830038300383008630038
100243003722511002682954825100101210000101000050427731313001830037300372829632876710010201000020300003003730037111002110910101000010003666101610102963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  umlsl v0.2d, v8.2s, v9.s[1]
  movi v1.16b, 0
  umlsl v1.2d, v8.2s, v9.s[1]
  movi v2.16b, 0
  umlsl v2.2d, v8.2s, v9.s[1]
  movi v3.16b, 0
  umlsl v3.2d, v8.2s, v9.s[1]
  movi v4.16b, 0
  umlsl v4.2d, v8.2s, v9.s[1]
  movi v5.16b, 0
  umlsl v5.2d, v8.2s, v9.s[1]
  movi v6.16b, 0
  umlsl v6.2d, v8.2s, v9.s[1]
  movi v7.16b, 0
  umlsl v7.2d, v8.2s, v9.s[1]
  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)033f51inst 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)9fa0a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042006515139258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415139668010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100010010111116112006101600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064349801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100010010111116112006101600001002006520065200652006520065
1602042006415639258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa8a9accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420086151051278001212800001280000626400001120032200512006032280012208000020240000200512005111160021109101016000010000010030311625211716200572401160000102005220257200522005220052
160024200601510452780012128000012800006264000001200322005120051322800122080000202400002005120051111600211091010160000102030100303116252111616200482201160000102005220232200612005220052
160024200511500512780012128000012800006264000011200322005120051322800122080000202400002005120051111600211091010160000100000100303111634422165200482201160000102005220225200522005220052
160024200511500452780012128000012800006264000011200322005120051322800122080000202400002006020051111600211091010160000100000100373111725211126200482401160000102005220233200522005220052
16002420051151045278001212800001280000626400000120041200512006032280012208000020240000200512005111160021109101016000010000010033311625211166200482201160000102005220223200522005220052
16002420051150045278001212800001280000626400001120032200512006032280012208014020240000200512005111160021109101016000010000010040311625211616200482201160000102005220259200522006120052
1600242006015005118680012128000012800006264000011200322005120051322800122080000202400002005120051111600211091010160000100000100403111625211166200482201160000102005220200200522005220052
16002420051150045278001212800001280000626400001120032200512005132280012208000020240000200512005111160021109101016000010000010040311625211166200482201160000102005220202200522005220052
1600242005115004527800121280000128000062640000112003220051200513228001220800002024000020051200511116002110910101600001048000100403111625211177200482201160000102005220176200522005220052
1600242005115104527800121280000128000062640000112004120060200603228001220800002024000020051200511116002110910101600001000001004031116252111616200482201160000102005220204200522005220052

Test 6: throughput

Count: 12

Code:

  umlsl v0.2d, v12.2s, v13.s[1]
  umlsl v1.2d, v12.2s, v13.s[1]
  umlsl v2.2d, v12.2s, v13.s[1]
  umlsl v3.2d, v12.2s, v13.s[1]
  umlsl v4.2d, v12.2s, v13.s[1]
  umlsl v5.2d, v12.2s, v13.s[1]
  umlsl v6.2d, v12.2s, v13.s[1]
  umlsl v7.2d, v12.2s, v13.s[1]
  umlsl v8.2d, v12.2s, v13.s[1]
  umlsl v9.2d, v12.2s, v13.s[1]
  umlsl v10.2d, v12.2s, v13.s[1]
  umlsl v11.2d, v12.2s, v13.s[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e373f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120204300582240704167132512011810012001810012000050096000003002030039300391665331499712010020012000020036000031748300391112020110099100100120000100000761031623317451200001003004031749300403004130040
12020430041225014467132512011810012000110012000050096000003172930040300391497331499712010020012000020036000030039317481112020210099100100120000100001761031623300361200001003004030040317493004031749
12020431748225004102512010010012000010012000050096000003172931748300391497331499712010020012000020036000030039300401112020110099100100120000100000761031633300361200001003004031749300403004031749
120204317482250186167132512011810012000110012000050096000003002030039300401665331670612010020012000020036000030040300391112020110099100100120000100000761021623300361200001003004031749300403174930040
120204300392250041671325120101100120001100120000500428362203002030039300401497331499812010020012000020036000030039300391112020110099100100120000100000761041633300361200001003004030043300403174930041
12020431748224014267132512011810012000010012000050096000003002030039300391497331670612010020012000020036000030039317481112020110099100100120000100000761031632317451200001003004030041300403004131749
120204300402250184102512010010012000010012000050096000003002030039300391497331670612010020012000020036000031748300391112020110099100100120000100000761031632300371200001003004130040317493004030041
120204300402250704402512010010012000010012000050099000003002131748300391497331499712010020012000020036000030039300401112020110099100100120000100000761021623300391200001003004031749300403004130040
120204300392380025167132512011810012001810012000050096000003002031748300401665331670612010020012000020036000031748300391112020110099100100120000100000761031632300361200001003004030040317493004031749
120204300392380184102512010010012000110012000050096000003002030039300401665331670612010020012000020036000031748300391112020110099100100120000100000761031632300361200001003174930040300413004030041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030407080b18191e1f373f4e51inst 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)9fa1a8acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430042238000000900410251200271012000010120000504283400010300213099730040149963150191200102012000020360000300393003911120021109101012000010000075200023161918300360120000103004030040300403004030040
1200243003922500000000040025120010101200001012000050960000015300203003930039149963150191200102012000020360000300393003911120021109101012000010000075200315161615300360120000103004030040300403004030040
1200243003922400000000061025120010101200001012000050960000005300203003930039149963150191200102012000020360000300393003911120021109101012000010000075205316161617300360120000103004030040300403004030040
120024300392250000000004084725120010101200001012000050960000005300203003930039149963150191200102012010720360000300393003911120021109101012000010000075205316161414300360120000103004030040300403174930040
1200243003923100000000040025120010101200001012000050960000015300203003930039149963150191200102012000020360000300403004011120021109101012000010000075205316161414300370120000103004030040300403004030041
1200243003922500000000061025120010101200171012000050960000015300203003930039149963167281200102012000020360000300393003911120021109101012000010000075200315161717300360120000103004030040300403004030040
1200243003922500000000040025120011101200001012000050960000015300203003930039166773150201200102012000020360000300393003911120021109101012000010000075205315161616300360120000103004032567300403004130041
1200243003923100000000040025120011101200001012000050990000015300203003930040149963150201200102012000020360000309223003911120021109101012000010000075205316161611300360120000103174930040300403004030041
1200243003922500000000040025120010101200011012000050990000015300203009332569149963150191200102012000020360000300393095111120021109101012000010000075205315161118300360120000103004230923300413004030043
1200243003922500000000141025120027101200001012000050960000015300203092230039149963150191200102012000020360000300403004011120021109101012000010000075205317161517300360120000103004030040300403004030041