Apple M1 Microarchitecture Research by Dougall Johnson

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

SABAL2 (vector, 4S)

Test 1: uops

Code:

  sabal2 v0.4s, v1.8h, v2.8h
  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)03091e3f4e51inst 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)a0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372200612548251000100010003983131301830373037241532895100010003000308530371110011000000073116112630100030383038303830383038
100430372200612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
100430372200612548251000100010003983131301830373037241532895100010003000303730371110011000000073132112630100030383038303830383038
1004303722001492548251000100010003983131301830373037241532895100010003000303730371110011000000073116112700100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220156842548251000100010003983131301830373037241532895100010003000303730371110011000010373116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220378612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sabal2 v0.4s, v1.8h, v2.8h
  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)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)9fa8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500001242954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
1020430037225000038229548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000018710021622296340100001003003830038300383003830038
1020430037225000041822954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100009710021622296340100001003003830038300383003830038
10204300372250000612954825101121001001610010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021623296340100001003003830038300383003830038
102043003722500005062954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300863003830038
102043003722500005972954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000712021622296340100001003003830038300383003830038
102043003722500004202954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
102043003722500004772954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710031622296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021732296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003724000000001032954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000300006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383008430038
10024300372250000000842954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10025300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000001472954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722400001800612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sabal2 v0.4s, v0.8h, v1.8h
  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)03070b181e1f3a3f4e51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000710011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000710011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000710011621296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000710011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010013710011611296340100001003003830038300383003830038
10204300372250001200612953925101001001000011710149500427731303005430037300372826632874510275200101662043000030037300371110201100991001001000010000710011612296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000710021621296340100001003003830038300383003830038
10204300372250001200612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000710011611296340100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000710011611296340100001003003830038300383003830038
10204300372250011210811172954825101001251000010010000500427731303001830037300852826532874410100204100002003000030037300372110201100991001001000010000710011614296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500200061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000000176295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003007830037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710160201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000082295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010560640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sabal2 v0.4s, v1.8h, v0.8h
  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)03081e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100125100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000307101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003008930086300383003830085
102043003722500726295482510128100100001001014962742773131300543008530084282653287451010020010000200300003003730037111020110099100100100001001007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001001307101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224127149295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500132612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300733003830038
1002430037224000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722501890942954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sabal2 v0.4s, v8.8h, v9.8h
  movi v1.16b, 0
  sabal2 v1.4s, v8.8h, v9.8h
  movi v2.16b, 0
  sabal2 v2.4s, v8.8h, v9.8h
  movi v3.16b, 0
  sabal2 v3.4s, v8.8h, v9.8h
  movi v4.16b, 0
  sabal2 v4.4s, v8.8h, v9.8h
  movi v5.16b, 0
  sabal2 v5.4s, v8.8h, v9.8h
  movi v6.16b, 0
  sabal2 v6.4s, v8.8h, v9.8h
  movi v7.16b, 0
  sabal2 v7.4s, v8.8h, v9.8h
  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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111216112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500392580100100801041248010550064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
1602042006415002102580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641510392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9faccfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420090151305129800101080000108000050640000211020039200672006732280010208000020240000200672006711160021109101016000010010031163142521155200552001160000102005920059200592005920059
16002420058150004527800101080000108000050640000111020039200582005832280010208000020240000200582005811160021109101016000010010028134132521166200552001160000102005920059200592005920059
160024200581500544527800101080000108000050640000111020039200582005832280010208000020240000200582005811160021109101016000010010028135152521154200552001160000102005920059200592005920059
16002420058150004527800101080000108000050640840211020039200582005832280010208000020240000200582005811160021109101016000010010028136253442255200642002160000102005920068200682005920059
16002420067150005127800101080000108000050640000111020039200582005832280010208000020240000200582005811160021109101016000010010027135152521155200552001160000102005920059200592005920059
16002420058150004527800101080000108000050640000111020039200582005832280010208000020240000200582005811160021109101016000010010027137152521155200552001160000102005920059200592005920059
16002420058150004527800101080000108000050640000211020039200582005832280010208000020240000200582005811160021109101016000010010029136162521155200552001160000102005920059200592005920059
16002420058150094527800101080000108000050640000111020039200582005832280010208000020240000200582005811160021109101016000010010028136253442254200552001160000102005920068200592005920059
16002420058150004527800101080000108000050640000211020039200582005832280010208000020240000200672005811160021109101016000010010031166252522145200554001160000102005920068200592005920059
16002420058150094527800101080000108000050640000111020039200582005832280010208000020240000200582005811160021109101016000010010028136152521155200552001160000102005920059200592005920059

Test 6: throughput

Count: 16

Code:

  sabal2 v0.4s, v16.8h, v17.8h
  sabal2 v1.4s, v16.8h, v17.8h
  sabal2 v2.4s, v16.8h, v17.8h
  sabal2 v3.4s, v16.8h, v17.8h
  sabal2 v4.4s, v16.8h, v17.8h
  sabal2 v5.4s, v16.8h, v17.8h
  sabal2 v6.4s, v16.8h, v17.8h
  sabal2 v7.4s, v16.8h, v17.8h
  sabal2 v8.4s, v16.8h, v17.8h
  sabal2 v9.4s, v16.8h, v17.8h
  sabal2 v10.4s, v16.8h, v17.8h
  sabal2 v11.4s, v16.8h, v17.8h
  sabal2 v12.4s, v16.8h, v17.8h
  sabal2 v13.4s, v16.8h, v17.8h
  sabal2 v14.4s, v16.8h, v17.8h
  sabal2 v15.4s, v16.8h, v17.8h
  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)03080b191e373f51inst 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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400693000000050251601001001600171001600005001280000040029400394004019973320006160100200160000200480000400484003911160201100991001001600001000103010110316254003601600001004004040217400404004040040
160204400392990000041251601001001600001001600005002398999040029400394004919973319997160100200160000200480000400484003911160201100991001001600001000000010110316234003601600001004004040049400404004040049
1602044004830000000199251601171001600001001600005002398999040020400394003919973320006160100200160000200480000400404003911160201100991001001600001000000010110316324004501600001004004940040400404004040040
160204400393000000041441601001001600001001600005001280000040020400394003919973320007160100200160000200480000400484004811160201100991001001600001000000010110216334003601600001004004040040400404004040050
160204400482990100050251601171001600001001600005001280000140029400484003919973319997160100200160000200480000400394003911160201100991001001600001000000010110316334003601600001004004940040400404004040049
160204400393000020050251601171001600001001600005002398999040020400394003919973319997160100200160000200480000400394003911160201100991001001600001000003010110316334003601600001004004040049400494004940040
1602044003930000000715251601001001600171001600005001280000140020400394004819973319997160100200160000200480000400394003911160201100991001001600001000000010110316334003601600001004004040049400494004040049
160204400393000000041251601001001600001001600005002398999040020400484003919973319997160100200160000200480000400394004911160201100991001001600001000140010110216234004521600001004004940049400494004040049
160204400393000000083251601001001600171001600005002398999040020400394004819973320007160100200160000200480000400484003911160201100991001001600001000000010110316334003601600001004004940040400404004040049
1602044003930000001741251601171001600001001600005001280000040020400484003919973319997160100200160000200480000400394003911160201100991001001600001000106010110316324003601600001004004040041400494004040049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f373f4e51inst 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)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)9fa0a1a6a7a8a9acc5cdcfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400492994000000017720025160027101600171016000050239899911540029400394003919996320019160010201600002048000040048400401116002110910101600001000000000010022811013162112512400360206160000104004140040400404004940040
16002440039300100001264196096025160010101600171016000050128000011540029400484003919996320019160010201600002048032140048400391116002110910101600001000000022250010022831025162112525400450207160000104004040040400494004040040
160024400482991000000054177390199161095121611901516111461138766321540505406624059020189532034316165920161635224837654063740749101160021109101016000010222002563300101108310141342113125403744206160000104059740676406084033840829
16002440811306210113131719114413328362027116157812161551111616935019979361154033140827407642013963201291617992016159320485517406484050014116002110910101600001000000000010022841027172112714400360209160000104004040040400494004040049
16002440039300100000001746025160010101600001016000050128000011540020400394004819996320019160010201600002048000040039400481116002110910101600001000000000010022841014162112714400450207160000104004040040400414004040041
1600244003930010000000055025160010101600001016000050239899911540020400394004019996320019160010201600002048000040040400391116002110910101600001000000000010022841014162111227400360209160000104004040049400404004940040
1600244004829910000000055025160010101600001016000050128000021540020400394003919996320019160123201600002048000040039400481116002110910101600001000000000010022841027162112727400360209160000104004940040400404004040040
1600244003929910000000055025160010101600001016000050239899911540020400484003919996320028160010201600002048000040039400481116002110910101600001000000000010022841027162111428400360209160000104004940040400494004040040
1600244004830010000000055025160027101600001016000050239899911540020400394003919996320028160010201600002048000040039400481116002110910101600001000000000010022841028162112126400860206160000104004940040400504004940049
1600244003930010000000046025160010101600171016000050128000011540020400394003919996320029160010201600002048000040049400391116002110910101600001000000000010022841027162112727400360206160000104004040049400404004140040