Apple M1 Microarchitecture Research by Dougall Johnson

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

SDOT (vector, 16B)

Test 1: uops

Code:

  sdot v0.4s, v1.16b, v2.16b
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220103254825100010001000398313130183037303724153289510001000300030853037111001100000073116112646100030383038303830383038
1004303723961254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722661254825100010001000398313030183037303724153289510001000300030373037111001100020073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722082254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sdot v0.4s, v1.16b, v2.16b
  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)031e3a3f4e51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001001071012162229634100001003003830038300383003830038
10204300372240098529548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250045061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216232963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216232963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sdot v0.4s, v0.16b, v1.16b
  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)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)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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000053629548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010210000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
1020430037224000000072629548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300853003830038

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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225034629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sdot v0.4s, v1.16b, v0.16b
  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)03070a181e1f3f4e51inst 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)696b6d6edispatch 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)9fa0a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251100061295482510100100100001001000050042773133001803003730037282727287401010020010008200300243003730037111020110099100100100001000000011171711611296500100001003003830038300383003830038
102043003722511000612954825101001001000010010000500427731330018030037300372827272874110100200100082003002430037300372110201100991001001000010000833011171711611296500100001003008630179300383003830038
102043003723300000103295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000005252954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000018000071021622296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300180300373003728265328745101002001000020030000300373003711102011009910010010000100001120000071021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383022530038
10204300372250000061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000083000071021622296340100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000003000071021622296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
102043003722500060612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000710216222963417100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000106402162229630010000103003830038300383003830038
100243003722500612954825100101010000121000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000036402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000054156402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000166402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100004706402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000033156402162229695010000103003830038300383003830038
100243003722500612954825100101010024101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000096402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100004236402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100004106402162229630010000103003830038300383003830038
100243003722400612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000036402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sdot v0.4s, v8.16b, v9.16b
  movi v1.16b, 0
  sdot v1.4s, v8.16b, v9.16b
  movi v2.16b, 0
  sdot v2.4s, v8.16b, v9.16b
  movi v3.16b, 0
  sdot v3.4s, v8.16b, v9.16b
  movi v4.16b, 0
  sdot v4.4s, v8.16b, v9.16b
  movi v5.16b, 0
  sdot v5.4s, v8.16b, v9.16b
  movi v6.16b, 0
  sdot v6.4s, v8.16b, v9.16b
  movi v7.16b, 0
  sdot v7.4s, v8.16b, v9.16b
  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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200901500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011231633200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011331632200611600001002006520065200652006520065
1602042006415003925801001008000011580000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010003001011331633201491600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011331633200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000421141011331633200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000131011441633200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000451011331633200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001441011331633200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000031011331632201271600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000531011431643200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

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)5f6061696b6d6escheduler 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
16002420059150452580012128000012800006264000011520027020046200463228001220801322024000020046200461116002110910101600001046010041811182021181820043215160000102025420047200472004720047
160024200461504525800121280000128000062640000015200310200502005032280012208000020240000200502005011160021109101016000010533100418311720212181820047215160000102023020047200512005120047
160024200501504525800121280000128000062640000115200270200462005032280012208000020240000200462004611160021109101016000010101003484172021181720043215160000102022020047200472004720047
16002420046150452580012128020812800006264000011520031020050200503228001220800002024000020050200501116002110910101600001044751004411521724422181720047230160000102022420051200512004720047
16002420046150452580012128000012800006264000011520027020046200463228001220800002024000020046200461116002110910101600001020100418411720211181720043215160000102021520047200512005120047
160024200501504525800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010101004411521724422181720047230160000102018720051200472005120051
16002420046150452580012128000012800006264000011520031020050200503228001220800002024000020050200501116002110910101600001000100418411724211171720043215160000102018820051200512004720047
1600242004615045258001212800001280000626400001152002702004620046322800122080000202400002004620046111600211091010160000102010041841172021171720043215160000102018520047200472004720047
160024200461504525800121280000128020962640000115200270200462004632280012208000020240000200462004611160021109101016000010101003184172021117720043215160000102017420047200472004720047
1600242004615045258001212800001280000626400001152002702004620046322800122080000202400002004620046111600211091010160000103175100441162172442271720047230160000102019120051200472004720051

Test 6: throughput

Count: 16

Code:

  sdot v0.4s, v16.16b, v17.16b
  sdot v1.4s, v16.16b, v17.16b
  sdot v2.4s, v16.16b, v17.16b
  sdot v3.4s, v16.16b, v17.16b
  sdot v4.4s, v16.16b, v17.16b
  sdot v5.4s, v16.16b, v17.16b
  sdot v6.4s, v16.16b, v17.16b
  sdot v7.4s, v16.16b, v17.16b
  sdot v8.4s, v16.16b, v17.16b
  sdot v9.4s, v16.16b, v17.16b
  sdot v10.4s, v16.16b, v17.16b
  sdot v11.4s, v16.16b, v17.16b
  sdot v12.4s, v16.16b, v17.16b
  sdot v13.4s, v16.16b, v17.16b
  sdot v14.4s, v16.16b, v17.16b
  sdot v15.4s, v16.16b, v17.16b
  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)03090b18191e1f373f51inst 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)9fa1a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400483100000001741251601171001600171001600005001280000140020400394004819973320006160100200160000200480000400484003911160201100991001001600001000000010110116114004501600001004004940050400404004940040
16020440039300000000171095251601171001600171001600005002398999140029400484003919973320006160100200160000200480000400394004811160201100991001001600001000050010110116114003601600001004010840049400404004040040
160204400482990000001750251601171001600171001600005001280000040020400394004819973320006160100200160000200480000400484003911160201100991001001600001000030010110116114003601600001004004040040400504004040049
160204400483000000001750251601001001600171001600005001280000140029400484004819973319997160100200160000200480000400484003911160201100991001001600001000000010110116114003601600001004005040049400404004040049
160204400483000000001741251601171001600171001600005001280000140020400394003919973320006160100200160000200480000400484003911160201100991001001600001009010010110116114004501600001004004040049400494004040049
16020440048300000000041251601001001600001001600005002398999140029400394004819973320006160100200160000200480000400394004811160201100991001001600001000000010110116114003601600001004004040049400404004040049
16020440039300000000041251601001001600001001600005001280000040029400394003919973320006160100200160000200480000400484003911160201100991001001600001000010010110116114003601600001004005340041400494004040040
16020440048299000090041251601171001600001001600005001280000040020400484003919973320006160100200160000200480000400394004811160201100991001001600001000130010110116114003601600001004004140049400404004940040
160204400392990000001750251601001001600171001600005002398999140020400394003919973319997160100200160000200480000400394004811160201100991001001600001000000010110116114004501600001004004040040400414005040040
16020440039300000000051251601001001600171001600005001280000140029400484003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004005340049400404004940049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f373a3f51inst 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)5f6061696b6d6edispatch 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)9fa0a1a8a9acc2cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440049299000000170717251605481016001710160000501280000011040029040048400391999632001916001020160000204800004003940039111600211091010160000100600000100241632171642217164004504112160000104004940040400404004940040
160024400393000000000052251600271016001710160000501280000011040020040039400391999632001916001020160000204800004004840039111600211091010160000100000000100241352101631216174004504012160000104004040049400404004040040
1600244003930000000000162251600101016000010160000501280000011040020040039400391999632001916001020160000204800004004840039111600211091010160000100000000100221621181642217164003602012160000104004040041400494004040040
16002440089300000000006725160010101600001016000050128000001104002904003940039199963200281600102016000020480000400394003911160021109101016000010000000010024652151621216164003604012160000104005440049400494004040040
1600244003930000000000522516001010160000101600005012800000104002004003940039200113200191600102016000020480000400394003911160021109101016000010000000010022621141621216144003602018160000104004440040400494004040049
1600244003930000000017046251600101016000010160000501280000011040020340039400391999632001916001020160000204800004003940039111600211091010160000100000000100241652161642116164003604012160000104005440040400404004040040
160024400393000000000071725160010101600001016000050239899910040020040039400391999632001916001020160000204800004003940039111600211091010160000100000000100241622141622218174003604112160000104004040040400404004040040
16002440039300000000005225160010101600001016000050128000011040029040039400391999632002816001020160000204800004004840039111600211091010160000100000000100221641201632217164003602012160000104004140049400404004040040
160024400483000000000052251600101016001710160000501280000011040020040039400481999632001916001020160000204800004003940039111600211091010160000100000000100221341191642217184003604112160000104004040040400414004040040
160024400393000000000052251600101016000010160000501280000011040020040039400391999632001916001020160000204800004003940039111600211091010160000100000000100241641171632219164003604112160000104004040041400404004040040