Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLAH (by element, 8H)

Test 1: uops

Code:

  sqrdmlah v0.8h, v1.8h, v2.h[1]
  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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037220251254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
1004303722088254825100010001000398313130183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037231261254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
1004303723661254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
1004303723661254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
1004303723661254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038
10043037230250254825100010001000398313030183037303724153289510001000300030373037111001100073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlah v0.8h, v1.8h, v2.h[1]
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa8acc2cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001001000710121622296342100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000070710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121623296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001002001710121622296340100001003003830038300383003830038
10204300372250161295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826525287451010020010000200300003003730037111020110099100100100001000000710131622296341100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa6acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640416342963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010030640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006312954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlah v0.8h, v0.8h, v1.h[1]
  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)030818191e1f3a3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010020127101161129634100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200101662003000030037300371110201100991001001000010001127101161129668100001003003830038300383003830038
10204300372240001200612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000127101161129634100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000127101161129634100001003003830038300383003830038
10204300372250000006312954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000187101161129634100001003003830038300383003830038
1020430037225000000103295482510100100100001001000050042773130300183003730037282656287451010020010000200300003003730037111020110099100100100001000097101161129634100001003003830038300383003830038
102043003722400100061295482510100100100001001000050042773130300183003730037282653287451025520010000200300003003730037111020110099100100100001000137101161129634100001003003830038300383003830038
10204300372250000001032954825101001001000010010000500427731303001830037300372826532874510100200100002003049530037300371110201100991001001000010000127101161129634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000837101161129634100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000157101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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
1002430037224061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100180640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250614295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222970210000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222970210000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010100640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqrdmlah v0.8h, v1.8h, v0.h[1]
  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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430084225661295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250621295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722518105295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001002007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003751100211091010100001000000006403162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500054061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830229300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000901104295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000564061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500000635295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372240000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlah v0.8h, v8.8h, v9.h[1]
  movi v1.16b, 0
  sqrdmlah v1.8h, v8.8h, v9.h[1]
  movi v2.16b, 0
  sqrdmlah v2.8h, v8.8h, v9.h[1]
  movi v3.16b, 0
  sqrdmlah v3.8h, v8.8h, v9.h[1]
  movi v4.16b, 0
  sqrdmlah v4.8h, v8.8h, v9.h[1]
  movi v5.16b, 0
  sqrdmlah v5.8h, v8.8h, v9.h[1]
  movi v6.16b, 0
  sqrdmlah v6.8h, v8.8h, v9.h[1]
  movi v7.16b, 0
  sqrdmlah v7.8h, v8.8h, v9.h[1]
  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)03181e3f51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200881510083258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011121611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
160204200641500039258010010080315100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
16020420064150006662580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000029001011111611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
1602042006415100602580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000052001011111611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
160204200641500081258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100030001011111611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

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)5f60696d6e74scheduler 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)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200721502132225800121280000128000062640000112002720046200460322800122080000202400002005020050111600211091010160000103401002731162421166200432150160000102004720047200472004720047
160024200461500512580012128000012800006264000011200272004620046032280012208000020240000200462004611160021109101016000010001002831172021164200432150160000102004720047200472004720047
160024200461500662580012128000012800006264000011200272004620046032280012208000020240000200462004611160021109101016000010001002631142021166200432300160000102005120051200512005120051
160024200461500722580012128000012800006264000001200272004620046032280012208000020240000200462004611160021109101016000010001002831132021144200432300160000102004720051200512005120051
160024200461500452580012128000012800006264000001200312004620046032280012208000020240000200462005011160021109101016000010001003232142021134200472300160000102005120051200512005120047
1600242005015007225800121280000128000062640000112003120046200460322800122080000202400002005020046111600211091010160000100121003031172442254200432150160000102004720047200512004720047
160024200501500512580012128020812800006264000001200312005020046032280012208000020240000200462004611160021109101016000010001002931262441176200472300160000102004720051200512005120047
160024200461500512580012128000012800006264000011200272005020046032280012208000020240000200502005011160021109101016000010001002632242042244200432300160000102004720047200472005120047
160024200461500452580012128000012800006264000001200312005020050032280012208000020240000200502004611160021109101016000010001003362182442144200432300160000102004720047200512005120051
160024200501500512580012128000012800006264000001200312004620046032280012208000020240000200462004611160021109101016000010001002931232442234200432150160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

  sqrdmlah v0.8h, v12.8h, v13.h[1]
  sqrdmlah v1.8h, v12.8h, v13.h[1]
  sqrdmlah v2.8h, v12.8h, v13.h[1]
  sqrdmlah v3.8h, v12.8h, v13.h[1]
  sqrdmlah v4.8h, v12.8h, v13.h[1]
  sqrdmlah v5.8h, v12.8h, v13.h[1]
  sqrdmlah v6.8h, v12.8h, v13.h[1]
  sqrdmlah v7.8h, v12.8h, v13.h[1]
  sqrdmlah v8.8h, v12.8h, v13.h[1]
  sqrdmlah v9.8h, v12.8h, v13.h[1]
  sqrdmlah v10.8h, v12.8h, v13.h[1]
  sqrdmlah v11.8h, v12.8h, v13.h[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)03080918191e1f373f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043084323100000018171025120152100120052100120000500960000030020300393003915857314997120100200120000200360000300393003911120201100991001001200001000000007610216223003601200001003004030040300403004030040
120204301032250000000751352325120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393095111120201100991001001200001000000007610216223003601200001003004030040309233004030952
120204300392250000000768025120100100120000100120000500960000130020300393003915857314997120100200120000200360000300393003911120201100991001001200001000000007610216223003601200001003004030040309523004030040
120204300392250000000104025120100100120000100120000500960000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000007610216223003601200001003095230040300403004030040
120204300392250000000790025120100100120000100120000500960000130020300393095114973314997120100200120000200360000300393003911120201100991001001200001000000007610216223094801200001003004030040300403004030040
12020430039225000000083025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000007610216223003601200001003004030040300403004030040
120204300392250000000811025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000007610216223003601200001003095230040300403004030040
12020430039225000000061025120100100120000100120000500960000130932300393003914973314997120100200120000200360000300393003911120201100991001001200001000000007610216223003601200001003004030040300403004030040
1202043003922500000017104025120100100120052100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000001007610216223003601200001003004030040300403004030040
120204300392240000003641025120100100120000100120000500960000030020300393095114973314997120100200120000200360000300393003911120201100991001001200001000000007610216223003601200001003095230040300403004030040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)03191e373a3f4e51inst 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)5f60696d6edispatch 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)9fa0a1a6a8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024300402270000883405251200101012005210120000504394061113002130040300401499631501912001020120000203600003175030040111200211091010120000100000007522311141621164317470305120000103004030040300403004030040
1200243003922500006902512001110120000101200005099000011300203003930039166773167301200102012000020360000300393003911120021109101012000010000000752232241622264300360155120000103004030040300403004030040
120024309222250017047502512001010120000101200005096000011300203003930039149963150191200102012000020360000300393003911120021109101012000010000000752431161621164300370155120000103004030040300403004030040
1200243003922500001130251200101012000010120000509600001130021300403003915850315019120010201200002036000030039300391112002110910101200001000200075223121116212106300360155120000103004131751317513004030040
1200243092222500006740251200101012000010120000509600001130020300393003914996315019120010201200002036000030039300391112002110910101200001000000075223111016411410300360155120000103004030040300403004030040
12002430039225000082434052512002810120000101200005096000011300203003930039149963159021200102012000020360000300393004011120021109101012000010000100752262110164111010300360155120000103004030923300403004030040
1200243003922500006799882512001110120000101200005043940611131731300403003914996315019120010201200002036000030039300401112002110910101200001000010075243121016231563003601510120000103092330040309233004030040
12002430040225001032902512001010120000101200005042834001130932300393003914996315019120010201200002036000030922300391112002110910101200001000000075223216162114103003621510120000103004030040300413004130040
1200243004222500006902512001110120017101200005099000011300213004030039149963150191200102012000020360000317503003911120021109101012000010000000752231141621146300370155120000103004130040300403004030040
12002430040225000075025120010101200001012000050960000113090330039309221499631502012001020120000203600003003930039111200211091010120000100000007524311101621146317470305120000103004030040300403004030040