Apple M1 Microarchitecture Research by Dougall Johnson

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

BIT (vector, 16B)

Test 1: uops

Code:

  bit v0.16b, 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
1004203715156116872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
1004203716010516872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951152116830002037203711100110000073116111787100020382038203820382038
1004203715010516872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100030002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->1

Code:

  bit v0.16b, 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): 2.0037

retire (01)cycle (02)030b1e3a3f4e51inst 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)9fa8branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150039906119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071012162219791100001002003820038200382008620038
10204200371500006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071212162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071012162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071012162219791100001002003820038200382003820038
102042003715000013619687251010010010000100100005002847680200182003720037184223187651010020010000200300002003720037111020210099100100100001000071012162219791100001002003820038200382003820038
102042003715007206119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071012162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071012162219791100001002003820038200382003820038
102042003715000014519687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071012162219791100001002003820038200382003820038
10204200371500606119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071012162219791100001002003820038200382003820038
10204200371500606119687251010010010000100100005002847680200182003720037184223187451010020010000200300002003720037111020110099100100100001000071212162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e1f3a3f4e51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715506000661968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640416331978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500600611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500900611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038
1002420037150028800611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316341978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038
1002420037150019500611968725100101010000101000050284768020018200372003718444318767100102010000203000020037200371110021109101010000100000640316331978510000102003820038200382003820038

Test 3: Latency 1->2

Code:

  bit v0.16b, 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): 2.0037

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)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)9fa0a6a8a9acc3cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611967625101001001000010010000644284768002001820085200851842231874510100204100002003000020037200842110201100991001001000010000002071071011612197910100001002003820038200852003820038
102042013215001801031968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500120611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000100071011611197910100001002003820038200382003820038
10204200371500210611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842631874510100200100002003000020037200371110201100991001001000010000100071011611197910100001002003820038200382003820038
102042003715001501031968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000100071011611197910100001002003820038202302003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037201811842231874510100200100002003000020037200371110201100991001001000010000200071011611197910100001002003820038200382003820038
102042003715000264611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640416431978510000102003820038200382003820038
100242003715023182196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001002093640316441978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640416431978510000102003820038200382003820038
100242008415018961196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640416441978510000102003820038200382003820038
100242003715019861196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640316431978510000102003820038200382003820038
100242003715030961196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640316341978510000102003820038200382003820038
10024200371500120196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640416431978510000102003820038200382003820038
1002420037150661196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640416341978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001010640416431978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002030000200372003711100211091010100001000640416431978510000102003820038200382003820038

Test 4: Latency 1->3

Code:

  bit v0.16b, 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): 2.0037

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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500360611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200851110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000821968725101371001000010010000522284768012001820074200371842231874510100200101682043000020037200372110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037149000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500004411968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715001501031968725101001001000010010000500284768012001820037200371842231874510100200100002003000020037200371110201100991001001000010010071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002003000020037200371110201100991001001000010000071011611198250100001002003820038200382003820038
10204200371500988611968762101301001000010010000500284768012001820085200371842231878210100200100002003000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
1002420037150000000001561968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
10024200371500000011100611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010002000006403163319785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000016403163319785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
1002420037150000000005361968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
10024200371500000030000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
10024200371500000029100611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403163319785010000102003820038200382003820038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  bit v0.16b, v8.16b, v9.16b
  movi v1.16b, 0
  bit v1.16b, v8.16b, v9.16b
  movi v2.16b, 0
  bit v2.16b, v8.16b, v9.16b
  movi v3.16b, 0
  bit v3.16b, v8.16b, v9.16b
  movi v4.16b, 0
  bit v4.16b, v8.16b, v9.16b
  movi v5.16b, 0
  bit v5.16b, v8.16b, v9.16b
  movi v6.16b, 0
  bit v6.16b, v8.16b, v9.16b
  movi v7.16b, 0
  bit v7.16b, 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)03091e3f51inst 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)60696b6d6escheduler 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200901500038258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
1602042006315002138258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
160204200631500038258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
1602042006315002138258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
16020420063150027338258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
16020420063150021938258010010080000100800006446400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
160204200631510038258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111622200601600001002006420064200642006420064
160204200631500038258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
160204200631500038258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064
16020420063150039638258010010080000100800005006400001200440200632006332180100200800002002400002006320063111602011009910010016000010001011111611200601600001002006420064200642006420064

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307090a0b1e3a3f51inst 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)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242006115000100056278001212800001280000626400001152004002005020059321800122080000202400002005020050111600211091010160000100010037112117252111414200472201160000102005120051200512005120051
16002420050150002000119278001212800001280000626400000152003102005920059321800122080000202400002005920059111600211091010160000100010042113216344221616200562202160000102006020060200602005120060
1600242005915610100056298001212800001280000626400000152003102005920050321800122080000202400002005020059111600211091010160000100010042113216344121515200472402160000102006020060200512006020060
160024200591501010005627800121280000128000062640000015200400200502005032180012208000020240000200592005911160021109101016000010001004111311534421815200472402160000102006020060200602006020060
1600242005915020000062278001212800001280000626400000152003102005020050321800122080000202400002005020050111600211091010160000100010038112116344111514200562201160000102006020051200512005120060
160024200501502021005029800121280000128000062640000015200310200502005932180012208000020240000200502005011160021109101016000010001003982115252111515200472201160000102005120051200512005120051
160024200501501020005027800121280000128000062640000115200310200502005032180012208000020240000200502005011160021109101016000010001003882117342121715200562201160000102005120051200602005120060
16002420059150100000682980012128000012800006264000011520031020050202162021800122080000202400002005920059111600211091010160000101610041112218344121716201122401160000102006020131200602013820112
1600242014615130300062278001212800001280000626400001152004002005020059321800122080000202400002005020050111600211091010160000100010044113217344121817200472401160000102006020051200602005120060
1600242005915010102104429800121280000128000062640000015200400200592005932180012208000020240000200592005911160021109101016000010031004183215252121616200562401160000102006020051200512005120060

Test 6: throughput

Count: 16

Code:

  bit v0.16b, v16.16b, v17.16b
  bit v1.16b, v16.16b, v17.16b
  bit v2.16b, v16.16b, v17.16b
  bit v3.16b, v16.16b, v17.16b
  bit v4.16b, v16.16b, v17.16b
  bit v5.16b, v16.16b, v17.16b
  bit v6.16b, v16.16b, v17.16b
  bit v7.16b, v16.16b, v17.16b
  bit v8.16b, v16.16b, v17.16b
  bit v9.16b, v16.16b, v17.16b
  bit v10.16b, v16.16b, v17.16b
  bit v11.16b, v16.16b, v17.16b
  bit v12.16b, v16.16b, v17.16b
  bit v13.16b, v16.16b, v17.16b
  bit v14.16b, v16.16b, v17.16b
  bit v15.16b, 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)0307080a18191e1f373f4e51inst 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)9fa0a8a9acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044008230100000008251511025160100100160082100160000500543965104008040039400381997303200841601002001600002004800004003840038111602011009910010016000010000000010110117114003501600001004010040039400394008240039
160204400383000000000406111025160182100160082100160000500543965104001940099400382000803200571601002001600002004800004009940099111602011009910010016000010000000010110116114003501600001004010040100401004003940100
160204400993001000000426111025160182100160000100160000500540263304001940099401412002203199961601002001600002004800004003840057111602011009910010016000010000000010110116114009601600001004003940100401004010040039
160204400383001000000040025160100100160082100160000500128000004008040099400991997303200571601002001600002004800004009940099111602011009910010016000010000000010110116114003501600001004010040100401004003940039
1602044003830000000008261025160100100160082100160000500540263304008040099400992000803200571601002001600002004800004009940099111602011009910010016000010000000010110116114009601600001004003940039400394003940040
160204400383001000090827260251601821001600001001600005005402633040080400994003820008031999516010020016000020048000040099400991116020110099100100160000100000000101101161340124251600001004003940039400394010040058
160204400383000000000826111025160100100160082100160000500540263304001940038400991997303200571601002001600002004800004009940089111602011009910010016000010000000010110116114003501600001004010040100401004010040100
160204400993000000000040025160100100160000100160000500128000004001940038400991997303199961601002001600002004800004009940099111602011009910010016000010000000010110116114009601600001004010040100401004010040039
160204400383001000000824011025160100100160082100160000500128000004008040099400991997303199961601002001600002004800004003840038111602011009910010016000010000000010110116114009601600001004010040039400394010040100
160204400993000000000826111025160182100160082100160000500128000004008040099400381997303199961601002001600002004800004003840099111602011009910010016000010000000010110116114003501600001004010040100401004010040128

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304070a18191e1f373a3f4e51inst 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)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)9fa8acc5cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024401462990000000006602516001010160023101600005039974241104001940038400381999603200181600102016000020480000400384003811160021109101016000010000100223110341621127294014002080160000104003940039400584003940039
160024400382990000000006302516003310160000101600005012800001104001940038400571999603200371600102016000020480000400574003811160021109101016000010000100223110181621129184004202080160000104003940058400394003940039
1600244003829900000000016602516001010160000101600005012800001104002040039400381999603200181600102016000020480000400394003811160021109101016000010000100223110181621129234004402080160000104003940058400394003940039
1600244003830000000004206702516001010160001101600005047289511104001940038400571999603200371600102016000020480000400384003811160021109101016000010000100223120171621129174004402080160000104011340039400394003940039
16002440112300000000011218802516001010160106101600005012800001104001940062400381999603200371600102016000020480000400574003811160021109101016000010000100223110271621116274004402070160000104003940039400394003940113
160024400382990000000006302516001010160023101600005012800001104001940038400381999603200181600102016000020480000400384005711160021109101016000010030100223210291621129294005602070160000104003940113400754011340058
160024400383000000000004502516011610160000101600005012800001104001940038400381999603200181600102016000020480000400574003911160021109101016000010000100223110291621129294005604280160000104003940089400754003940058
160024400393000000000114602516001010160001101600005012800001104003840038400391999603200191600102016000020480000400384003911160021109101016000010000100223110291621115294006302080160000104005840039400584011340039
16002440038300000000000671492516001010160001101600005012800001104005640057400571999603200371600102016000020480000400574003811160021109101016000010000100223110271621129294005602080160000104005840039400584004040039
16002440057300000000018104502516001010160000101600005013200001104002040038400381999603200921600102016000020480000400384003811160021109101016000010000100223110241621128174006102080160000104005840113400584003940039