Apple M1 Microarchitecture Research by Dougall Johnson

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

LD2 (single structure, B)

Test 1: uops

Code:

  ld2 { v0.b, v1.b }[1], [x6]
  nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop
  mov x0, 1
  mov x1, 2
  mov x8, 0

(no loop instructions)

1000 unrolls and 1 iteration

Retires (minus 60 nops): 3.000

Issues: 3.002

Integer unit issues: 0.000

Load/store unit issues: 1.000

SIMD/FP unit issues: 2.002

retire (01)cycle (02)03070a0e0f1e223a3f43464951inst issue (52)~issue fp/simd (54)~issue ld/st (55)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing ld/st (5a)huge thing fp/simd (5b)5f696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op ld/st (7d)~map op fp/simd (7e)~map lookup ld/st (80)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst fp/simd load (98)inst ldst (9b)9da0a1a3a6a8a9acafb5bbdcache load miss (bf)cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)dfe0eaebecld/st retires (ed)? fp/simd (ee)f5f6f7f8fd
6300528482214161400214989279311111630030042004100020001000500023881322801280592844431030001000200010004000282212799711610011000100001000031003001100121313812102887083338513471977834213812164444227988148791257412982100020002853728406282192852128292
630042836221416130031495828162011162943004200210002000100050002385442278328320284083103000100020001001400028313283821161001100010000100002100000310000031360010227722333686391960433283822144343227978147101297513493100020002817328113281762821828341
630042829721115120020517428125000162803002200210002000100050002381602278328356282933103000100020001000400028314281091161001100010000100002100010010011101357610111705333877351976333733820174237227944151911302513312100020002839628360283722840128554
630042850321310120021494728133010163573000200010002000100050002385822275128388284063103000100020001000400028299283851161001100010000100002100100110001131394710256722734109411966333493816123842327988143261263413086100020002825128278282182822928228
6300428472211151100415053281280011631130042002100020001000500023798822757284202829531030001000200010004000283672828611610011000100001000021006123100311213600999971063393537194793359380694442228001142731265813565100020002845628351283442851728339
630042827721215140070494528106111162653002200210002000100050002389322276828415283963103000100020001000400028243281961161001100010001100002100310010001131357310353706534009391955333373818124142228062145021297313422100020002819328154282552837628244
630042835221111120041501828161011162773004200010002000100050002381362276628227281693103000100020001000400028236284231161001100010000100000100000610001131391710164716934085371960233853815114046327980143141266813511100020002829128520284112846228381
63004283182111316004149322813410116144300220001000200010005000238895227622812428291310300010002000100040002838328314116100110001000010000210010011003113137959939724333798401949233943817204138228051139821256913635100020002818228449285932830728195
63004282962131315004150072808700116211300420041000200010005000238908227532831328298310300010002000100040002820028248116100110001000010000010011031003030140559997708533985361955134013813124339327892150431268814001100020002824228258282642832028429
630042853021216120001499628013111161133002200410002000100050002389752276828385285503103000100020001000400028482280481161001100010000100002100000110002121368810227720234227461948733973817114043227977148071231913655100020002822328347282932823328327

Test 2: Latency 1->3 roundtrip

Chain cycles: 3

Code:

  ld2 { v0.b, v1.b }[1], [x6]
  fmov x0, d0
  eor x8, x8, x0
  eor x8, x8, x0
  add x6, x6, x8
  mov x0, 1
  mov x1, 2
  mov x8, 0

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 3 chain cycles): 11.0047

retire (01)cycle (02)030708090a0b0e0f18191e1f22243a3f4d4e4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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 fp/simd load (98)inst ldst (9b)9d9fa0a1a3a6a8a9acafb5dcache load miss (bf)c2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eaebecld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
7020514004710490000001001010014069813970713933812935325801194013230041100023010030000100001264328670729820081263014002301400481400471305453131205701003020010000301606244010157518651402491400472150201100991004010010000100000100100000110000020100001100340231532213989940000666100002000040100140048140080140658140611140048
70204140047105001000000082010014003213943113933812935325801034010030003100003024930000100001264328669338820081263014002301400471400471305443131118701003020010000300006020010000500001400481400351150201100991004010010000100000100100000110000000100001100321021532213955940028666100002000040100140048140049140049140150140048
702041400471049000000000208000014002013943313933812934125801034010030003100003010030000100001264328669338820081263014009501400471400471305433131126701003020010000300006020010000500001400471400471150201100991004010010000100000100100060110000000100001100321021532213955940000666100002000040100140048140036140048140048140048
7020414004710490000000101010014003213943113933812935325801034010030003100003010030000100491264382669338820081263014002331400491400471305433131126701003020010000301586020010000500001400471400471150201100991004010010000100000100100000110001000100001100321021532213955940000666100002000040100140048140048140050140149140048
7020414004710490000000001010014003213943113933812935325801034010030003100003024930000100001264328669338820081263014002301400401400471305433131118701003020010000300006057410000500001400471400472150201100991004010010000100000100100000110000300100001100321021332213968040000666100002000040100140048140048140048140048140048
7020414004710490000000101010114003313947013933812935325801034010030007100003010030000100491265635669338820081263014002301400481400471305753131118701003020010000300006020010000502661400481400361150201100991004010010000100000100100000110000000100001100321021332213954440024066100002000040100140048140048140048140048140048
7020414004710490000000001010014003213943113933812935325801034010030003100003010030000100001264328669338820081263014003101400471400471305433131126701003036010000300006020010000500001400471400471150201100991004010010000100000100100000110000000100001000321021532213955940000666100002000040100140080140080140051140048140048
702041400471049000000000100001400321394311393381293532580103401003000310000301003000010000126432866933882008126301400230140047140047130572313111870100302001000030000602001000050000140047140050115020110099100401001000010000010010000011000041183100001100321021532213955940000606100002000040100140048140051140048140036140048
702041400351049000000100528810014003213943113932512935325801034010930003100003010030000100001264328669338820081263114002301400471400471305433131120704413020010000300006020010000500001400471400491150201100991004010010000100000100100030110000000100001120321021532213955940000666100002000040100140048140052140048140144140048
70204140035104900000110013010014003213943113933812935325801034010030003100003010030000100001264328669338820081263014002301400471400471305433131126701003020010000300006020010000500001400471400471150201100991004010010000100001100100000110000000100001100321021532213955940000666100002000040100140054140050140048140048140048

1000 unrolls and 10 iterations

Result (median cycles for code, minus 3 chain cycles): 11.0049

retire (01)cycle (02)03080b0e0f18191e1f22243a3f4d4e4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)5f60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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 fp/simd load (98)inst ldst (9b)9d9fa0a3a6a8acafb5bbdcache load miss (bf)c5cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebecld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
70025140053104900110010100140035139491139343129356258001340010300031000030010300001000012647716693388200812630014002614005014005013056831311757001030020100003000060020100005000014005014009611500211091040010100001000001010000110000431000010100319000051210002413986240000969100002000040010140051140051140151140051140036
70024140047104900000010000140035139491139325129356258001040010300001000030010300001000012647716693869200794510014001114003514005013055331311757001030020100003000060020100005000014005014003511500211091040010100001000001010000110000001000000100314000021210002413957440000069100002000040010140036140051140036140051140048
70024140047104900000000000140035139446139343129341258001340010300031000030010300001000012647716693535200812630014001114005014003513056531311617001030020100003000060020100005000014005014004711500211091040010100001000001010000110000001000010100314000021210002413957240000960100002000040010140048140048140036140051140051
70024140035104800010010100140035139448139373129342258001040010300031000030010300001000012647716692791200794511014002614003514005013056831311617001030020100003000060020100005000014005014003511500211091040010100001000001010000110000101000000000314000021210002213956940000006100002000040010140086140051140048140110140083
70024140050104900000000000140035139492139325129356258001040010300031000030010300001000012647716693535200794510014002314003514004713056831311757001030020100003000060388100005000014004714005811500211091040010100001000001010000110000031000010100314000021200003213957240000909100002000040010140036140036140051140051140051
70024140047104900000010000140020139491139344129356258001340010300001000230010300001000012651226692887200812630014002614003514004713056831311757001030020100003000060020100005000014005014004711500211091040010100001000001010000110000053851000010100316800021210003513986440000969100002000040010140051140037140051140154140051
70024140035104900000000100140035139446139343129356258001040010300031000030010300001000012647196693535200816970014002614005014004713056831311757001030020100003000060388100005000014005014004711500211091040010100001000001010000110000001000010100314000021210004313955740000990100002000040010140051140051140051140051140036
70024140035108000000010100140020139491139325129356258001340010300031000030010300001000012647486692791200816970014001114005014003513056831311757001030020100003000060020100005000014005014003511500211091040010100001000001010000110000101000010000314000021210002213955740000999100002000040010140051140051140036140051140036
70024140035104900000010000140035139487139325129356258001040010300001000030010300001000012647716693535200812630014001114004714004713056531311737001030020100003000060020100005000014005014004711500211091040010100001000001010000110000001000010000314000021200003213957040000099100002000040010140036140051140051140051140081
7002414003510480010000000014003513944613933812935358800104001030003100003001030000100001264719669358320081263001400231400501400501305533131175700103002010000300006002010000500001400471400351150021109104001010000100000101000011000000100001000031400002170003213957240000909100002000040010140036140048140051140048140051

Test 3: Latency 2->3 roundtrip

Chain cycles: 3

Code:

  ld2 { v0.b, v1.b }[1], [x6]
  fmov x1, d1
  eor x8, x8, x1
  eor x8, x8, x1
  add x6, x6, x8
  mov x0, 1
  mov x1, 2
  mov x8, 0

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 3 chain cycles): 11.0458

retire (01)cycle (02)030508090b0e0f181e2223243a3f4d4e4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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 fp/simd load (98)inst ldst (9b)9d9fa0a1a3a6a8a9acafb5bbdcache load miss (bf)dtlb miss (c1)c2c5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)eaebecld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
702051408871054100100071001140670139866139974129987258010640100300061000030100300001000012699626713069201725740140434014068214068513096439131777701003020010000300006020010000500001404581404581150201100991004010010000100000100100021110001011100001111000321031291114019240000131013100002000040100140459140686140686140459140683
7020414068210521100010110001404431398661399741297622580106401003000310000301003000010000126808767238212017257401406610140685140685131190313177770100302001006430000602001000050000140458140458115020110099100401001000010000010010002211000202110000010110032101129111401954000013130100002000040100140459140683140683140686140683
70204140685108812010002000014067014033113997512977525801064010030012100003010030000100001268087672382120172574014043401404581406821309643131553701003020010000300006020010000500001406821407461150201100991004010010000100000100100021110001211100001111100321011291114019540000101010100002000040100140683140686140459140459140686
7020414045810531100000200001406701402791399741299872580106401003000610000301003000010000126810567239652017301511406580140458140685131190313178070100302001000030000602001000050000140458140682115020110099100401001000010000010010001211000211110000111100032101129111401954000013013100002000040100140683140459140683140683140686
7020414045810511100110210011406701402791399741299872580106401003000310000301003000010000126808767239652017257411404340140458140458131187313177770100302001000030000602001000050000140458140711115020110099100401001000010000110010003111000200410000111100032101171114019440000131313100002000040100140686140686140459140686140686
7020414045810541101000200001406751402761399721299872580106401003000610000301003000010000126996267239652017257411406610140685140685130964313178070100302001000030000602001000050000140685140682115020110099100401001000010000010010001101000201410000011100032101129111401954000001013100002000040100140459140686140686140459140686
7020414068210521101000100001404431402761399741299852580103401003000610000301003000010000126994667238212017257411406610140682140685130964313155370100302001000030000602001000050000140682140682115020210099100401001000010000110010002301000101110000111110032101129111399694000013130100002000040100140686140686140459140686140683
7020414068210541101000700001404431402791399741297632580106401003000310000301003000010000126996267130692017257401406610140458140685131190313177770100303891000030000602001000050000140685140682115020110099100401001000010000010010003201000158111000011111003210112911139969400000013100002000040100140459140686140459140683140459
7020414068510531100010210001406751402791399721299852580106401003000610000301003000010000126996267239652014029501406580140685140458131190313178070100302001000030000602001000050000140458140682115020110099100401001000010000010010002111000101110000111100032101129111401954000013013100002000040100140686140686140687140459140692
70204140458105210011002100014044314027913997412998725801034010030006100003010030000100001269962672396520140295114043401404581406851311903131780701003020010000300006020010000500001404581406821150201100991004010010000100001100100012010002021100001111000321011291114019540000131313100002000040100140459140459140686140459140459

1000 unrolls and 10 iterations

Result (median cycles for code, minus 3 chain cycles): 11.0301

retire (01)cycle (02)03050708090b0e18191e1f22233f4d4e4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)5f60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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 fp/simd load (98)inst ldst (9b)9d9fa0a1a3a6a8a9acafb5bbdcache load miss (bf)dtlb miss (c1)c2cfd0icache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)eaebecld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
70025140594105200000000001014024413986213975312956425800104001030003100003001030000100001266650670356420141197111404400140259140259130776313116270010300201000030000603941000050000140464140069115002110910400101000010000110100000110000000100001010031400051215413978040000969100002000040010140260140465140037140260140260
70024140259105200000000100014024413948813975312956425800104001030000100003001030000100001264728669283920111784001402350140259140036130554313138370010300201000030000600201000050000140464140036115002110910400101000010000110100000110000000100001010031403041215413998440000906100002000040010140037140260140037140465140260
70024140096105200000000101014044913948813955112956425800134001030003100003001030000100001268532671336620079595001402350140464140036130554313116270010300201000030000600201000050000140464140036115002110910400101000010000010100000110000000100001010031400041204513955840000999100002000040010140260140260140465140260140465
70024140259105200000000101014024413948813975312956425800104001530003100003001030000100001266650671336620111784011400120140036140464130554313116270010300201000030000600201000050000140464140464115002110910400101000010000010100000010000000100000010031400061224413978040000009100002000040010140465140037140465140465140465
70024140036105300000100001014002113970013955112934225800134001030003100003001030000100001266650670356420111784011402350140259140036130980313116270010300201000030000600201000050000140259140259115002110910400101000010000010100000110000000100001010031400041224413955840000996100002000040010140260140037140260140037140260
70024140259105200000000001014002113970013955112998325800134001030000100003001030000100001264728670356420079595011402350140036140259130776313158970010300201000030000600201000050000140036140259115002110910400101000010000010100000110000000100001010031400061225413978040000009100002000040010140260140037140037140465140260
70024140259104900000100601014002113970013955112976825800104001030003100003001030000100001264728670356420111784011402350140263140259130554313116270010300201000030000600201000050000140259140464115002110910400101000010000010100000110000000100001010031400041225413955840000000100002000040010140465140260140260140465140465
70024140036104900000000101014024413970013975312976825800134001030000100003001030000100001268532671336620141197001402350140259140259131195313116270010300201000030000600201000050000140036140036115002110910400101000010000010100000110000000100001000031403061224413978040000069100002000040010140037140260140465140260140037
700241404641052000000001000140244139700139326129564258001340010300031000030010300001000012647286703564201117840114023501402591402591309803131383700103002010000300006002010000500001402591404641150021109104001010000100000101000001100005120100001010031400061225413998540000060100002000040010140260140260140037140260140348
70024140259104900000100000014024513948813932612956425800134001030000100003001030000100001266650669283920111784001402350140036140259130776313116270010300201000030000600201000050000140036140464115002110910400101000010000010100000110000000100001000031400041225413955840000990100002000040010140037140465140037140260140260

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  movi v0.16b, 0
  movi v1.16b, 0
  ld2 { v0.b, v1.b }[1], [x6]
  mov x7, x6
  mov x8, x6
  mov x9, x6
  mov x10, x6
  mov x11, x6
  mov x12, x6
  mov x13, x6

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.6263

retire (01)cycle (02)03090b0e0f1e1f2223373a3f4346494e4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)60696d6edispatch stall (70)74scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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 fp/simd load (98)inst neon or fp (9a)inst ldst (9b)9d9fa0a1a3a6a8a9acafb5b6bbdcache load miss (bf)c2cfd5d6ddinst fetch restart (de)e0e7? int output thing (e9)eaebld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
400205501303750000250109315012621010002624023610016016180000100160000800005004000681923081150048501145010203436324010020080000160000200800003200005011750103112402011009910010080000160000800000100800000238002600268002661200015110116115013210100800003200001005007350073500765006850068
4002045010237600003200040205005221000034240288100160189800001001600008000050040006819272231501865010850067034343240100200800001600002008000032000050067501011124020110099100100800001600008000001008000002380025000800200102901511011611501050006800003200001005010950068501035011950157
40020450149376000068630810160505007121010002624070010016018880000100160000800005004001351916967150149500675018003536524010020080000160000200800003200005008950075112402011009910010080000160000800000100800000080000002680000601929015110116115011610100800003200001005012350148501385007950068
400204500723750000001095050087200150262403141001603318000010016000080000500400059191696705010750078500670035424010020080000160000200800003200005010350090112402011009910010080000160000800001100800000080026000800266126001511011611501050000800003200001005011550068500685010250104
40020450103375000032000171005012200041026240314100160396800001001600008000050040012619239920500595008650086211433224010020080000160000200800003200005015250075112402011009910010080000160000800000100800000080019004680019612029015110116115006900100800003200001005014150150501075011550068
4002045006737500000000317050088210000262401001001604408000010016000080000500400127192364415008350113501080383242401002008000016000020080070320000501035007811240201100991001008000016000080000010080000023800000008001901192901511011611501051006800003200001005006850102501535006850120
40020450067375000031000205050052010101502624010010016000080000100160000800005004000671916967150121500675010800324240100200800001600002008000032000050101501181124020110099100100800001600008000011008000002380000002680025002529015110116115010510100800003200001005011950117501235010450068
40020450102375000032000595050125210061026240350100160000800001001600008000050040006519237461500595006750230041365240100200800001600002008000032000050100500891124020110099100100800001600008000001008000002380000000800266019001511011611500831000800003200001005010250068501095010950102
4002045010237600003100045415012921010002624010010016034680000100160000800005004001261921642150089501955010101136424010020080000160000200800003200005009550112112402011009910010080000160000800000100800000080026000800266102901511011611500991006800003200001005010350108500685007850087
40020450103375101131000831501372100270262402651001602148000010016000080000500400126191971615004850119500670273602401002008000016000020080000320000501085019511240201100991001008000016000080000010080000023800260008001901252301511011611500640006800003200001005010050141501505007950068

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.6260

retire (01)cycle (02)0307080a0b0e0f18191e1f22373a3f4346494e4f51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~dispatch int (56)~dispatch fp/simd (57)~dispatch ld/st (58)huge thing int (59)huge thing ld/st (5a)huge thing fp/simd (5b)5f6061696d6edispatch stall (70)74scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op ld/st (7d)~map op fp/simd (7e)~map lookup int (7f)~map lookup ld/st (80)~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 fp/simd load (98)inst neon or fp (9a)inst ldst (9b)9d9fa0a1a3a6a7a8a9acafb5b6bbdcache load miss (bf)c2c5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0e7? int output thing (e9)eaebecld/st retires (ed)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
400025501093750000000049012810500562101000262402471016023780000101600008000050400000191846021550060500685004402935024001020800001600002080000320000500795007911240021109101080000160000800000108000002380019000198001961202300150711744421784443315013700806080000320000105005350080500455005650045
400024501053750000000025010050064210100026240247101602378000010160000800005040006719184602155006050044500440113622400102080000160000208000032000050055500711124002110910108000016000080000010800000238001900020800196102300150281744341784449265008910866080000320000105008050080500805008050080
400024500793750000000032005605006421010002624001010160237800001016000080000504000001911249215500605007950079003342400102080000160000208000032000050079500791124002110910108000016000080000010800000238001900019800196119000150281744351784417395015300866080000320000105004550045500455010750045
400024500793750000000015700519450088210100090240010101601798000010160000800005040005919184582155003650079500440353582400102080000160000208000032000050079500791124002110910108000016000080000010800000238001900019800196119230015030205533171044243050131001066080000320000105008050080500805008050084
400024500723751010000025005605004020000262402471016023780000101600008000050400000191846011550060500555007901935824001020800001600002080000320000500795009811240021109101080000160000800000108000002380020000080020012000015030205434171055362350266001066080000320000105007450053500805010650072
40002450055374000000002501216050064210100026240291101600008000010160000800005040005719112491155004750055500440353582400102080000160000208000032000050079500441124002110910108000016000080000010800000080019000080019001923001503020553517844353450080001066080000320000105008050080500805008050064
400024500443750010000025011913500292100002724001010160101800001016000080000504000681918460215500545008350052035346240010208000016000020800003200005007950071112400211091010800001600008000001080000023800200001980020012023001502820452017105516345015400860080000320000105004550080500805008050080
400024501063750000000025002700501582101000262402471016023780000101600008000050400059191124911550025500795007900358240010208000016000020800003200005007950079112400211091010800001600008000001080000023800200002080000612023001502817443617845263050065101060080000320000105008050080500805004550045
400024500793750000000025017705002921010002624016410160093800001016000080000504000591920235115500605004450065035358240010208000016000020800003200005006850071112400211091010800001600008000001080000023800190002080019602623001502820108381713124303750197001316180000320000105005350069500805008050080
40002450064375000000002501121050064210100026240010101602378000010160000800005040000019148211155003350044500790032324001020800001600002080000320000500735005211240021109101080000160000800000108000002380019010080019602023001503020495231784427325035100866080000320000105008050080500805008050045