Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL2 (vector, 2D)

Test 1: uops

Code:

  sqdmlal2 v0.2d, v1.4s, v2.4s
  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)a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723961254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000094216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal2 v0.2d, v1.4s, v2.4s
  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)030708090a1e1f3a3f4e51inst 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)9fa0a6a8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251001000612954825101001001000010010000500427731313001803003730037282727287411010020010008200300243003730037111020110099100100100001000000111720011611296500100001003003830038300383003830038
10204300372251001000612954825101001001000010010000500427731313001803003730037282727287401010020010008200300243003730037111020110099100100100001000000111718011611296510100001003003830038300383003830038
10204300372251001000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000710131633296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000522427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000710131633296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000710131633296340100001003003830038300383003830038
10204300372250000900612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000710131633296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000710131633296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000710131633296340100001003003830038300383003830038
102043003722500000004702954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000712131633296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018030037300372826527287451010020010000200300003003730037111020110099100100100001000000000710131633296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03083a3f4e51inst 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)9fa1a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510019101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000001640216222963010000103003830038300383003830083
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640316222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216322963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlal2 v0.2d, v0.4s, v1.4s
  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)03080b181e3f4e51inst 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)9fa8acc2cfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500007402954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
102043003722500001952954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100060710011611296340100001003003830038300383003830038
102043003722500005332954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
102043003722500004352954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
102043003722500006312954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
102043003722500004842954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
102043003722500001852954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
102043003722500006842954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038
102043003722500004512954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa0a1a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250001183295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640616342963010000103003830132300383003830038
1002430037225057061295482510010101000012100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640416352963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000001640416432963010000103003830038300383003830038
100243008422500061295488310010101000010100005042773133001830037300372828732876710010201000020300003003730037211002110910101000010000000640416432963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730180111002110910101000010020000640316342963010000103003830038300383003830038
100243003722500082295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640416642963010000103003830038300383003830038
1002430037225039061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640416342963010000103003830038300383003830038
100243003722500082295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640316342963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640316432963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010221000640316342963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal2 v0.2d, v1.4s, v0.4s
  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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030226300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010020071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030133300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722504412954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030225300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728305328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001001306402162229630010000103003830038300383003830038
1002430037225000942954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767101602010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103008530038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal2 v0.2d, v8.4s, v9.4s
  movi v1.16b, 0
  sqdmlal2 v1.2d, v8.4s, v9.4s
  movi v2.16b, 0
  sqdmlal2 v2.2d, v8.4s, v9.4s
  movi v3.16b, 0
  sqdmlal2 v3.2d, v8.4s, v9.4s
  movi v4.16b, 0
  sqdmlal2 v4.2d, v8.4s, v9.4s
  movi v5.16b, 0
  sqdmlal2 v5.2d, v8.4s, v9.4s
  movi v6.16b, 0
  sqdmlal2 v6.2d, v8.4s, v9.4s
  movi v7.16b, 0
  sqdmlal2 v7.2d, v8.4s, v9.4s
  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)9fa0a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200911506999892580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000010114316442006101600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010114416452006101600001002006520065200652006520065
160204200641500832580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000013010114316542006101600001002006520065200652006520065
1602042006415012392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010113416342006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000010115516542006101600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520076200643228010020080000200240000200642006411160201100991001001600001000000010115416552006101600001002006520065200652006520065
1602042006415039392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000110113416442006101600001002006520065200652006520065
16020420064150138392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000010113516352006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000010114516552006101600001002006520065200652006520065
160204200641516392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000010115316342006101600001002006520065200652006520065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

retire (01)cycle (02)03071e3f51inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9faccfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242009715010452780012128000012800006264000011020032200512005132280012208000020240000200512005111160021109010101600001001004331136252111414200482201160000102005220052200522005220052
16002420051150004527800121280000128000062640000115200322005120051322800122080000202400002006020060111600211090101016000010010041114211344221416200572402160000102006120061200612006120061
16002420060150005129800121280000128000062640000015200412006020060322800122080000202400002006020060111600211090101016000010010038134114252111611200482201160000102005220052200522005220052
160024200511500045278001212800001280000626400001110200322005120051322800122080000202400002037120051211600211090101016000010010042134120252111416200482201160000102005220052200522005220052
1600242005115000140278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211090101016000010010037135113252111310200482201160000102005220052200522005220052
160024200511510066278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211090101016000010010037135115252111311200482201160000102005220052200522005220052
160024200511500045278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211090101016000010010034135120252111311200482201160000102005220052200522005220052
160024200511500045278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211090101016000010010060135117252111310200482201160000102005220052200522005220052
160024200511500045278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211090101016000010010041135113252211811200482201160000102005220052200522005220052
160024200601500045278001212800001280000626400001110200322005120051322800122080000202400002005120060111600211090101016000010010036135117252111118200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  sqdmlal2 v0.2d, v16.4s, v17.4s
  sqdmlal2 v1.2d, v16.4s, v17.4s
  sqdmlal2 v2.2d, v16.4s, v17.4s
  sqdmlal2 v3.2d, v16.4s, v17.4s
  sqdmlal2 v4.2d, v16.4s, v17.4s
  sqdmlal2 v5.2d, v16.4s, v17.4s
  sqdmlal2 v6.2d, v16.4s, v17.4s
  sqdmlal2 v7.2d, v16.4s, v17.4s
  sqdmlal2 v8.2d, v16.4s, v17.4s
  sqdmlal2 v9.2d, v16.4s, v17.4s
  sqdmlal2 v10.2d, v16.4s, v17.4s
  sqdmlal2 v11.2d, v16.4s, v17.4s
  sqdmlal2 v12.2d, v16.4s, v17.4s
  sqdmlal2 v13.2d, v16.4s, v17.4s
  sqdmlal2 v14.2d, v16.4s, v17.4s
  sqdmlal2 v15.2d, v16.4s, v17.4s
  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): 0.2503

retire (01)cycle (02)03080b18191e1f373f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044004930000004200715025160100100160017100160000500128000014002940039400391997303200071601002001600002004800004004840039111602011009910010016000010000000010110116114003601600001004004040041400404004040049
16020440039300000000151025160100100160000100160000500128000014002940276400911998003200061601002001600002004800004003940049111602011009910010016000010000000010110116114006801600001004004040050400494004040049
160204400493000000001750025160100100160017100160000500128000014003040039400391997303199971601002001600002004800004003940040111602011009910010016000010000000010110116114004601600001004004940072400404004040049
160204400393000000001761025160117100160000100160000500132000014002040039400391997303199971601002001600002004800004003940049111602011009910010016000010000000010110116114003601600001004004040040400504004940050
16020440049300000000061025160117100160000100160000500128000014002040039400391997303199971601002001600002004800004003940048111602011009910010016000010000000010110116114003601600001004004940040400504004940050
16020440048300000000041025160100100160017100160000500132000014002940049400481997303199971601002001600002004800004003940049111602011009910010016000010000000010110116114003601600001004005040049400404004140040
160204400483000000000512525160100100160000100160000500538718814002040148400391997303199971601002001600002004800004004840039111602011009910010016000010000000010110116114003601600001004004040050400404004040072
16020440039300000000051025160117100160000100160000500128000014002040039400491997373199971601002001600002004800004003940048111602011009910010016000010000000010110116114006801600001004004140040400414004040049
160204400393000000001412525160117100160001100160000500128000014002040039400391997303199971601002001600002004800004003940049111602011009910010016000010000000010110116114004501600001004007240040400404004140041
16020440040300000000041025160100100160000100160000500128000014002040039400391997303200071601002001600002004800004004940039111602011009910010016000010000000010110116114006801600001004004040040400504004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e373f51inst 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)9fa7a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440039300024056251600101016000010160000501280000114002040040400391999632002816001020160000204800004003940039111600211091010160000100001002462230162112323400460155160000104004040040400404004040040
160024400393000390522516001010160000101600005012800000140020400404003919996320019160010201600002048000040039400481116002110910101600001000010024622191642226234003603010160000104004040040400404004040040
16002440039300000522516001010160000101600005012800000140020400404004919996320019160010201600002048000040039400391116002110910101600001000010024622221642221214003603010160000104004040040400404004040040
16002440039300000522516001010160000101600005012800000140020400454004819996320053160010201600002048000040039400391116002110910101600001000010024622221642221224003603010160000104004040053400404005040040
1600244003930000052251600101016000010160000501280000014002040040400391999632001916001020160000204800004003940049111600211091010160000100001002231125162112222400360155160000104004040040400404004040040
1600244003929900046251600101016000010160000501280000114002040040400491999632001916001020160000204800004003940039111600211091010160000100001002231122162112122400362155160000104004040040400404005040040
16002440039299060046251600101016000010160000501280000114002040051400391999632001916001020160000204800004003940039111600211091010160000100001002231123162112122400360156160000104004040040400404004040040
16002440039300000522516001010160000101600005024388650140020400404004819996320019160010201600002048000040039400391116002110910101600001000010024622221642223224003603010160000104005040040400404004040040
1600244003930000046251600101016000010160000501280000114002040052400391999632001916001020160000204800004003940039111600211091010160000100001002231121162111624400360155160000104004040040400404004040050
16002440039300000462516001010160000101600005012800001140020400404003919996320019160010201600002048000040039400391116002110910101600001000010024622221642224244003703010160000104004040040400404004040040