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, 8B)

Test 1: uops

Code:

  bit v0.8b, v1.8b, v2.8b
  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)696d6edispatch 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
10042037150821687251000100010002646802018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100030002037203711100110000394116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000300020372037111001100032073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
100420371501031687251000100010002646802018203720371572318951000100030002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100030002037203711100110000973116111787100020382038203820382038

Test 2: Latency 1->1

Code:

  bit v0.8b, v1.8b, v2.8b
  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)0308091e3a3f4e51inst 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)9faccdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000330611968725101001001000010010000500284768012001802003720037184223187451010020010000200300002003720037111020110099100100100001000071003163319791100001002003820038200382003820038
102042003715000150611968725101001001000010010000500284768002001802003720037184223187451010020010000200300002003720037111020110099100100100001000071003163319791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001802003720037184223187451010020010000200300002003720037111020110099100100100001000071013163319791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001802003720037184223187451010020010000200300002003720037111020110099100100100001000071013163319791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001802003720037184223187451010020010000200300002003720037111020110099100100100001000071014164319791100001002003820038200382003820038
102042003715000210611968725101001001000010010000500284768012001802003720037184223187451010020010000200300002003720037111020110099100100100001000071013163319791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001802003720037184223187451010020010000200300002003720037111020110099100100100001000071013163319791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001802003720037184223187451010020010000200300002003720037111020110099100100100001000071013163319791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001802003720037184223187451010020010000200300002003720037111020110099100100100001000071013163319791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001802003720037184223187451010020010000200300002003720037111020110099100100100001000071013163319791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000000611968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000006408167819785010000102003820038200382003820038
10024200371500000000005721968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000006408168719785010000102008520038200382003820038
1002420037150000010000611968725100101010000101000050284768002001820037200371844403187671001020100002030000200372003711100211091010100001000000006406167819785010000102003820038200382003820038
10024200371500000002700611968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000006408168819785010000102003820038200382003820038
10024200371500000001800611968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000006407167819785010000102003820038200382003820038
1002420037150000000000611968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000006408168719785010000102003820038200852003820038
1002420037150000000000611968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000006407167819785010000102003820038200382003820038
1002420037150000000001611968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000306408168719822010000102003820038200382003820038
1002420037150000000000611968725100101010000101000050284768002001820037200371844403187671001020100002030000200372003711100211091010100001000000006407168719785010000102003820038200382003820038
1002420037150000000000611968725100101010000101000050284768012001820037200371844403187671001020100002030000200372003711100211091010100001000000006407167619785010000102003820038200382003820038

Test 3: Latency 1->2

Code:

  bit v0.8b, v0.8b, v1.8b
  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)0307191e3a3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000025119687251010010010000125100005002847680020018200372003718422031874510100200100002003000020037200371110201100991001001000010000071011643197910100001002003820038200382003820038
102042003715010006119687251010010010000100100005002847680120018200372003718422031874410100200100002003000020037200371110201100991001001000010000071411611198460100001002003820038200382003820038
1020420037150000023219687251012510010000100100006262847680020018200372003718422031874510100200100002003000020037200371110201100991001001000010002971011611197910100001002003820038200382003820038
10204200371490100611968725101001251000010010000500284768012001820037200371842203187451010020010000200300002003720037111020110099100100100001000206371011611197910100001002003820038200382003820038
102042003715000006319687251010012510000100100005002847680020018200372003718422031874410125200100002003000020037200371110201100991001001000010000071011711197910100001002003820038200382003820038
102042003715000006119687251012512510000125100005002847680020018200372003718422031874510100200100002003000020037200371110201100991001001000010001371031611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842203187451010020010000200300002003720037111020110099100100100001000515971011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422031874510100200100002003000020037200371110201100991001001000010002071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018200372003718422031874510100200100002003000020037200371110201100991001001000010000071011743197910100001002003820038200382003820038
102042003715000006119687251012512510000125100006262847680120018200372003718422031874510100200100002003000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038

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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010019640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010020640216221978510000102003820038200382003820038
100242003715027611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715002511968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010026640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010006640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010023640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010013640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: Latency 1->3

Code:

  bit v0.8b, v1.8b, v0.8b
  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)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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042007315000000006311967625101001001000010010000500284896302001820037200371842231874510100200100002003000020037200371110201100991001001000010000002403071011611197910100001002003820038200382003820038
10204200371500000120061196872510100100100001001000050028476801200182003720037184223187451010020010000200300002003720037111020110099100100100001000000100071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200300002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476800200182003720037184223187451010020010498200300002003720037511020110099100100100001000000309071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200300002003720037111020110099100100100001000000200071011611197910100001002003820038200382003820085
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200300002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200300002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200300002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200300002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200300002003720037111020110099100100100001000030000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006403162219785010000102003820038200862008420038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000013886751967625100101010000101000050284768002001820037200371844481876710010201000020300002003720037111002110910101000010002000404306402242219785010000102003820038200382003820038
10024200371500000120611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000010006402162219785010000102003820038200382003820038
10024200371500000001561968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000821968725100101010000101000050284768002001820037200371844431876710010201000020300002003720037111002110910101000010000000326402162219803010000102003820038200382003820038
100242003715000000010281968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020300002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  bit v0.8b, v8.8b, v9.8b
  movi v1.16b, 0
  bit v1.8b, v8.8b, v9.8b
  movi v2.16b, 0
  bit v2.8b, v8.8b, v9.8b
  movi v3.16b, 0
  bit v3.8b, v8.8b, v9.8b
  movi v4.16b, 0
  bit v4.8b, v8.8b, v9.8b
  movi v5.16b, 0
  bit v5.8b, v8.8b, v9.8b
  movi v6.16b, 0
  bit v6.8b, v8.8b, v9.8b
  movi v7.16b, 0
  bit v7.8b, v8.8b, v9.8b
  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)031e1f3a3f51inst 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)696d6escheduler 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
160204200651500003825801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011141611200601600001002006420064200642006420064
160204200631510003825801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
160204200631500003825801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
160204200631500005925801001008000010080000500640000200442006320063921801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
1602042006315000022825801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
160204200631500003825801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
160204200631500003825801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
16020420063150000480525801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
160204200631510003825801001008000010080000500640000200442006320153321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064
160204200631500003825801001008000010080000500640000200442006320063321801002008000020024000020063200631116020110099100100160000100001011111611200601600001002006420064200642006420064

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a1e3a3f51inst 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)9fa8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200741500004427800121280000128000062640000115200312005020050321800122080000202400002006320050111600211091010160000100001003281110266212692005622001160000102005120051200512005120060
16002420059150000442780012128000012800006264000011520031200502005032180012208000020240000200762005911160021109101016000010000100308516259223992004722001160000102005120051200512006020051
160024200501500005027800121280000128000062640000115200402005920059321800122080000202400002008520068111600211091010160000100001003585162454211072005624002160000102006020060200602006020060
160024200501500025027800121280000128000062640000115200402005020059321800122080000202400002008520059111600211091010160000100001006411529237422992004722001160000102005120051200512005120051
1600242005015020050298001212800001280000626400000152004020059200503218001220800002024000020063200591116002110910101600001000010032115272444226102006524002160000102006020060200512005120060
160024200591500005029800121280000128000062640000115200402005920059321800122080000202400002006320059111600211091010160000100001003284162672231092005624002160000102006020060200512006020060
1600242005015000043029800121280000128000062640000115200312005020059321800122080000202400002008520050111600211091010160000100001003511519216221972004724002160000102005120051200512005120051
160024200591500004427800121280000128000062640000115200402005020050321800122080000202400002008620050111600211091010160000100001003511529237422972005622002160000102005120060200602006020051
160024200591500005029800121280000128000062640000015200402005920059321800122080000202400002008520068111600211091010160000100001003511529244423792005624002160000102006020060200602006020060
160024200591500005029800121280000128000062640000015200402005920059321800122080000202400002008620059111600211091010160000100001003311526274623962005624002160000102006020060200602006020060

Test 6: throughput

Count: 16

Code:

  bit v0.8b, v16.8b, v17.8b
  bit v1.8b, v16.8b, v17.8b
  bit v2.8b, v16.8b, v17.8b
  bit v3.8b, v16.8b, v17.8b
  bit v4.8b, v16.8b, v17.8b
  bit v5.8b, v16.8b, v17.8b
  bit v6.8b, v16.8b, v17.8b
  bit v7.8b, v16.8b, v17.8b
  bit v8.8b, v16.8b, v17.8b
  bit v9.8b, v16.8b, v17.8b
  bit v10.8b, v16.8b, v17.8b
  bit v11.8b, v16.8b, v17.8b
  bit v12.8b, v16.8b, v17.8b
  bit v13.8b, v16.8b, v17.8b
  bit v14.8b, v16.8b, v17.8b
  bit v15.8b, v16.8b, v17.8b
  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)030b191e1f373f4e51inst 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)9fa6a8accfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204401243000000293400251601001001600001001600005001320000140019400384005719973032001516010020016000020048000040038400571116020110099100100160000100000101100116114010901600001004003940058400394003940039
160204400383000000061113251601231001600001001600005001280000140038400384003820007031999616010020016000020048000040057400381116020110099100100160000100000101102216114003501600001004003940039400964009640039
1602044003830000000820251601001001600781001600005001280000040019400384003820003031999616010020016000020048000040095400381116020110099100100160000100000101100116114003501600001004009640039400394003940096
1602044003830000300400251601001001600001001600005001280000040019400384003820003031999616010020016000020048000040038400951116020110099100100160000100000101100116124009201600001004003940096400394003940039
16020440038300000002751112516017810016000010016000050012800001400194003840038199730319996160100200160000200480000400954009511160201100991001001600001000101011001161140119211600001004003940105400394003940039
1602044003830010000400251601001001600001001600005005519418140076400384009520003031999616010020016000020048000040099400381116020110099100100160000100033101100116114003601600001004009640039400394003940039
1602044009530000000400251601001001600001001600005001280000040019400394003819973031999616010020016000020048000040038400381116020110099100100160000100000101100117114003501600001004003940039400394003940039
160204400383000000061111251601171001600001001600005005519418040076400384003819973031999616010020016000020048000040095400951116020110099100100160000100030101100128114003501600001004009640118401384003940096
1602044003830000000610251601001001600001001600005005519418140081400384003819973031999616010020016000020048000040095400951116020110099100100160000100010101100116114003501600001004003940039401024009640039
160204400393000012001240251601781001600001001600005001280000040019400384003819973031999616010020016000020048000040038400381116020110099100100160000100000101102116114003501600001004003940039401014003940096

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e373f4e51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400393000000511102516001010160000101600005012800001004001940185400382003103200181600102016000020480000400384003811160021109101016000010001002433511816211161640096208160000104010040039400394003940039
160024400383000008145025160010101600011016000050128000010040093400384003919996032001816001020160000204800004003840038111600211091010160000100010022328161621161640035208160000104010040039400394003940039
16002440038299000045025160010101600001016000050128000010540019400384003819996032001816001020160000204800004018540099111600211091010160000100010022829151621261340035208160000104003940100400394003940039
1600244010129900007100251600111016008210160000501280000100400194003840038199960320018160010201600002048000040038400381116002110910101600001000100228312161621116640096209160000104003940039400394003940039
160024400383000000450251600101016000010160000505362848115400194009940038199960320018160010201600002048000040038400381116002110910101600001000100228312171621116640035208160000104003940039400394010040040
16002440038300000045025160092101600001016000050128000011540019400384003819996032007916001020160000204800004003840038111600211091010160000100010022329261621151640182208160000104003940039400394003940039
160024400383000000670251600101016000010160000501280000110400194003840038199960320018160010201600002048000040185400991116002110910101600001000100228331161621116540035208160000104003940100401864010040039
16002440099300000067025160010101600001016000050128000011540019400384003819996032001816001020160000204800004003840038111600211091010160000100010022113121616411161640035208160000104003940039400394010040039
1600244003829900004502516001010160000101600005054382641104001940038400381999603200181600102016000020480000400384003811160021109101016000010001002283111616211161640036208160000104003940039400394003940039
160024400383000000710025160010101600001016000050128000001540019400384003819996032001816001020160000204800004003840099111600211091010160000100010022361161621116640096208160000104003940039401004003940039