Apple M1 Microarchitecture Research by Dougall Johnson

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

MLS (by element, 8H)

Test 1: uops

Code:

  mls v0.8h, v1.8h, v2.h[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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000973116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100004273116112630100030383038303830383038
100430372308425482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722636125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372308425482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372396125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls v0.8h, v1.8h, v2.h[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)0308181e1f3a3f4e51inst 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)9fbranch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000822954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710021622296344100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710121622296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710121622296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037301334110201100991001001000010000712121622296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710121622296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710121622296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710121622296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710121632296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710121622296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710131622296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa1accfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162329630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630110000103008530038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010206402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls v0.8h, v0.8h, v1.h[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)030708090a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acbbc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003008530038300383003830038
10204300372250000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030084300852110201100991001001000010000000000071011611296700100001003003830038300383003830038
10204300372240000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372240000000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000900612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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)9fa0a1a6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
1002430037225012061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
1002430037225000105295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000002306693163329630010000103003830038300383003830038
100243003722400061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
10024300372250624061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
10024300372240004044295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
100243003722403061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830085300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls v0.8h, v1.8h, v0.h[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)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250822954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372240912954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102021009910010010000100007101161129634100001003003830038300383003830038
102043003722533612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100007401161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000787101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000877101162129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100097101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000967101161129634100001003003830038300383003830038

1000 unrolls and 10 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100660640416442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010090640416342963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100930640416442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640416342963010000103003830038300383003830038
10024300372250612954825100101010000101000050428274113001830037300372828732876710010201016722300003003730037111002110910101000010000640316342963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001001020640416442963010000103003830038300383003830038
10024300372257266129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100810640416442963010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100960640416342963010000103003830038300383003830038
100243003722507262954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010090640316442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640416432963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.8h, v8.8h, v9.h[1]
  movi v1.16b, 0
  mls v1.8h, v8.8h, v9.h[1]
  movi v2.16b, 0
  mls v2.8h, v8.8h, v9.h[1]
  movi v3.16b, 0
  mls v3.8h, v8.8h, v9.h[1]
  movi v4.16b, 0
  mls v4.8h, v8.8h, v9.h[1]
  movi v5.16b, 0
  mls v5.8h, v8.8h, v9.h[1]
  movi v6.16b, 0
  mls v6.8h, v8.8h, v9.h[1]
  movi v7.16b, 0
  mls v7.8h, v8.8h, v9.h[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)03090b18191e1f3f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042008815020000022925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010003010114116112006101600001002006520065200652006520065
1602042022915000000038258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100015010111116112006101600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
16020420064150000018039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100084010111116112006101600001002006520065200652006520065
1602042006415000000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100099010111116112006101600001002006520065200652006520065
1602042006415100002403825801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116122006101600001002006520065200652006520065
160204200641500000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111117332006101600001002006520065200652006520065
1602042006415000000039258010010080000125800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100072010111116112006101600001002006520065200652006520065
16020420064150000012039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000101111161120061251600001002006520065200652006520065
16020420064151001100392580100100800001258000065064000012004520064200643228010020080000200240000200642006411160201100991001001600001000511010184149222012801600001002006520065200652006520065

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)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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200661500455180012128000012800006264000011520027200462004610228001220800002024000020046200461116002110910101600001040100258217202117620043215160000102004720047200472004720047
160024200461500425588001212800001280000626400000152003120050200503228001220800002024000020050200501116002110910101600001000100258212202114420043215160000102004720047200472004720051
1600242005015005165800121280000128000062640000015200312005020050322800122080000202400002005020050111600211091010160000104131002811322244222420047230160000102005120051200512005120051
160024200501500515680012128000012800006264000001520031200502005032280012208000020240000200502005011160021109101016000010411051003111322244222420047230160000102005120051200512005120051
16002420050150051538001212800001280000626400000152003120050200503228001220800002024000020050200501116002110910101600001001561003011324244224220047230160000102005120051200512005120047
1600242004615004560800121280000128000062640000115200272004620046322800122080000202400002005020046111600211091010160000101101003111326244226720047230160000102005120051200512005120047
16002420050150045538001212800001280000626400000152003120050200503228001220800002024000020050200501116002110910101600001000100258312202112420043230160000102004720047200472004720047
160024200461500515780012128000012800006264000001520031200502005032280012208000020240000200502005011160021109101016000010433100288214202114220043230160000102005120051200512005120051
1600242005015005153800121280000128000062640000015200312005020050322800122080000202400002005020050111600211091010160000102201002811324244224220047230160000102005120051200512005120047
16002420046150045558001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000100258214202112420043215160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

  mls v0.8h, v12.8h, v13.h[1]
  mls v1.8h, v12.8h, v13.h[1]
  mls v2.8h, v12.8h, v13.h[1]
  mls v3.8h, v12.8h, v13.h[1]
  mls v4.8h, v12.8h, v13.h[1]
  mls v5.8h, v12.8h, v13.h[1]
  mls v6.8h, v12.8h, v13.h[1]
  mls v7.8h, v12.8h, v13.h[1]
  mls v8.8h, v12.8h, v13.h[1]
  mls v9.8h, v12.8h, v13.h[1]
  mls v10.8h, v12.8h, v13.h[1]
  mls v11.8h, v12.8h, v13.h[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)03373f4e51inst 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
12020430058225041025120100100120000100120000500960000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001003000761011611309401200001003175030040300403004030043
12020430039225041025120100100120000100120000500960000030020300393003914973314997120100200120000200360000300393004211120201100991001001200001002830761011611300361200001003004030040300433004030040
12020430557225044025120100100120001100120000500960000030023300393003914973314997120100200120203200360000300393094311120201100991001001200001000990761011611300391200001003004030040300403004330043
12020430039225041025120117100120000100120000500960000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001002860761011611300361200001003004330040300403004330944
12020430039225141025120100100120000100120128500960000030023300393003914973314998120100200120000200360000300393004211120201100991001001200001001270761011611300361200001003004030040300403004030040
12020430039225044025120100100120000100120000500960000030023300393003914973314997120100200120000200360000300413003911120201100991001001200001002630761011611300361200001003004030040300433004030040
12020430039225041025120100100120000100120000500960000030020300423003914973315000120100200120000200360000300423003911120201100991001001200001003031761011601300361200001003004030040300403094430040
120204300392255343025120100100120000100120000500990000030924300393003914973314999120100200120000200360000300393003911120201100991001001200001003330761011611309191200001003004030040300433004030040
1202043003922504402512013110012000010012000050096000003002030943300391497331500012010020012000020036000030039300421112020110099100100120000100230761011611300361200001003004030040309443004030042
12020430039225041025120100100120000100120000500990000030924300393003914973314997120100200120000200360000300393003911120201100991001001200001003030761011611300361200001003004030040300403004330043

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f373f4e51inst 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)9fa0a1a7a8a9acc2cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430048225000210040025120010101200001012000050960000130020309423003914996315019120010201200002036000030039300391112002110910101200001001000307520416023300360120000103004030040300403004030998
120024300392250000004002512002710120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100000010207520316032300360120000103004030040300403004030040
120024300392250009004002512001010120000101200005096000003002030876300911499631611212001020120106203600003003930090211200211091010120000100020062407520316033300360120000103004030040300403004030040
120024300392250001200820251200101012000010120000509600000300203003930039149963150191200102012000020360000300393003911120021109101012000010000006907520316032300360120000103004030040300403004030040
120024300392250000014002512001010120000101200005096000013002030039300391499631501912001020120000203600003003930039111200211091010120000100000011407520316033300360120000103004030040309233004030041
1200243003922500000040025120010101200001012000050960000130020300393003914996315019120010201200002036000030039300391112002110910101200001000080007520416032300360120000103004030040309233004030040
12002430039232000000400251200101012000010120000509600000300213003930039149963150191200102012000020360000300393003911120021109101012000010000230607520316033309190120000103004230040300403004030040
12002430039225000000400251200101012000010120000509600001300203003930039149963150191200102012000020360000300393003911120021109101012000010000320307520316433300360120000103004030040300403004030040
12002430039225000000400251200461012000010120000509600000300203003930039149963150191200102012000020360000300393003911120021109101012000010000290007520316032300360120000103004030040300403004030040
12002430039225000000400251200101012000010120000509600000300203003930039149963150191200102012000020360000300393003911120021109101012000010000300307520216033300360120000103004030040300403004030040