Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLSH (by element, 4S)

Test 1: uops

Code:

  sqrdmlsh v0.4s, v1.4s, v2.s[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)03080b18191e1f3a3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000000061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722000000061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723000060061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722000000061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112702100030383038303830383038
1004303723000000061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037220000000842548251000100010003983130301830373037241532895100010003000303730371110011000210073116112630100030383038303830383038
1004303723000000061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722000000061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723000000061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722000000082254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlsh v0.4s, v1.4s, v2.s[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)0318191e1f3a3f4e51inst 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)9fa6a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043008422500240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131633296340100001003003830038300383003830038
102043003722500150061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730084211020110099100100100001000000710131633296340100001003003830038300383003830038
10204300372250024003853295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131633296340100001003003830038300383003830038
102043003722500330161295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131633296340100001003003830038300383003830038
102043003722500510061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131633296340100001003003830038300383003830038
102043003722500120061295482510100100100001001000050042773130300183003730037282653287451010020010000204300003003730037111020110099100100100001000000710141633296340100001003003830038300383003830038
1020430037224004590161295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131633296340100001003003830038300383003830038
102043003722500240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710141633296340100001003003830038300383003830038
102043003722500270061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131644296340100001003003830038300383003830038
102043003722500240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131633296340100001003003830038300383003830038

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)696b6d6edispatch 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000237006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006402162329630010000103003830038300383003830038
1002430037225000027006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000318006129548251001010100001010000504277313300183300373003728287328767100102010000203000030037300371110021109101010000100000006403163229630010000103003830038300383003830038
100243003722500006006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006403163229630010000103003830038300383003830038
1002430037225000012006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000072629548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000053629548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006403162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000006402162329630010000103003830038300383003830038
1002430037225000060034629548251001010100001010000504277313300180300373003728287328767100102010000203000030037300372110021109101010000100000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlsh v0.4s, v0.4s, v1.s[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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000037101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300862250061295482510100100100001001000050042773131300183003730037282653287451025320010000200300003003730037111020110099100100100001000037101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000037101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000067101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000037101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000817101161129634100001003003830038300383003830038
10204300372250261295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000037101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000037101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000162064021622296300010000103003830038300383003830038
10024300372250000000612954825100101010000101000071427867003001803003730037282873287671001020100002030000300373003711100211091010100001000000129064021622296300010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000153064021622296300010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000135064021622296300010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000000064021622296300010000103003830038300383008530038
100243003722500000300612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000144064021622296300010000103003830038300383003830038
100243003722500000150612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000120064021622296300010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000126064021622296300010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001803003730084282873287671001020100002030000300373003711100211091010100001000000174064021622296300010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000144064021622296300010000103003830038300383003830085

Test 4: Latency 1->3

Code:

  sqrdmlsh v0.4s, v1.4s, v0.s[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)030b18191e1f3f4e51inst 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)9fa0a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071021611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500036061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000747295482510100100100001001000050042773133001830037300372826532877910100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830227300383003830038
1020430037225000414061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0304080b18191e1f3a3f4e51inst 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)6061696d6edispatch 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)9fa0a1a6a8a9acc2c5cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000006129548251001010100001010000504277313103001830037300372828703287671001020100002030000300373003711100211091010100001000000000640004163429630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131530018300373003728287032876710010201000020300003003730037111002110910101000010000001200640004164429630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000000000640003163429630010000103022730038300383003830038
1002430037225000000006129548251001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000000000640004164429630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000000000640003164429630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000000000640003163429630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000000000640004164329630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000000000640004164429630010000103003830038300383003830038
1002430226225000000006129548451001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000020000640003164329630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313003001830037300372828703287671001020100002030000300373003711100211091010100001000000000640004163429630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlsh v0.4s, v8.4s, v9.s[1]
  movi v1.16b, 0
  sqrdmlsh v1.4s, v8.4s, v9.s[1]
  movi v2.16b, 0
  sqrdmlsh v2.4s, v8.4s, v9.s[1]
  movi v3.16b, 0
  sqrdmlsh v3.4s, v8.4s, v9.s[1]
  movi v4.16b, 0
  sqrdmlsh v4.4s, v8.4s, v9.s[1]
  movi v5.16b, 0
  sqrdmlsh v5.4s, v8.4s, v9.s[1]
  movi v6.16b, 0
  sqrdmlsh v6.4s, v8.4s, v9.s[1]
  movi v7.16b, 0
  sqrdmlsh v7.4s, v8.4s, v9.s[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)03081e3f51inst 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
16020420091150003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500014625801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500023125801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652013320065
16020420064151003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011211611200611600001002006520065200652006520065
160204200641500070425801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011211611201291600001002006520065200652006520065
160204200641500333925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a18191e1f3a3f51inst 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)5f60696d6escheduler 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)9fa0a1a6a7a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420065150101000005125800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000000100373121724422816200472300160000102005120051200512005120051
160024200501501000000057258001212800001280000626400000120031200502005032280012208000020240000200502004611160021109101016000010000000001003731215244221514200472300160000102005120051200512005120051
160024200501501010000051258001212800001280000626400001120027200462004632280012208000020240000200462004611160021109101016000010000000001003931214202111414200472150160000102004720047200472005120051
16002420046150001000005725800121280000128000062640000012003120050200503228001220800002024000020046200461116002110910101600001000001000100373121524422159200472300160000102005120051200512005120051
1600242005015010100000299258001212800001280000626400000120031200462005032280012208000020240000200502005011160021109101016000010000000001004061216904221515200432300160000102005120051200512005120051
16002420050150102000001412580012128000012800006264000001200312005020050312280012208000020240000200502005011160021109101016000010000000001004361215244221315200472300160000102005120051200512005120051
160024200501502030000063258001212800001280000626400000120027200502005032280012208000020240000200502005011160021109101016000010000000001004162216244121414200472300160000102005120051200512005120051
160024200501501000000051258001212800001280000626400000120031200502005032280012208000020240000200502005011160021109101016000010000000001004161216244221414200472300160000102005120051200512005120051
160024200501501010000074258001212800001280000626400000120027200502004632280012208000020240000200502005011160021109101016000010000000001004162214244221313200472300160000102005120051200512005120051
160024200501500000000051258001212800001280000626400000120031200502005032280012208000020240000200502005011160021109101016000010000000001004262213244221512200472300160000102005120051200512005120051

Test 6: throughput

Count: 12

Code:

  sqrdmlsh v0.4s, v12.4s, v13.s[1]
  sqrdmlsh v1.4s, v12.4s, v13.s[1]
  sqrdmlsh v2.4s, v12.4s, v13.s[1]
  sqrdmlsh v3.4s, v12.4s, v13.s[1]
  sqrdmlsh v4.4s, v12.4s, v13.s[1]
  sqrdmlsh v5.4s, v12.4s, v13.s[1]
  sqrdmlsh v6.4s, v12.4s, v13.s[1]
  sqrdmlsh v7.4s, v12.4s, v13.s[1]
  sqrdmlsh v8.4s, v12.4s, v13.s[1]
  sqrdmlsh v9.4s, v12.4s, v13.s[1]
  sqrdmlsh v10.4s, v12.4s, v13.s[1]
  sqrdmlsh v11.4s, v12.4s, v13.s[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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043030223000006600136025120100100120000100120000500960000030020325813003914973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
120204300392250000240041025120100100120000100120000500960000030020317433003914973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
1202043003922500002700136025120100100120000100120000500960000030020317533003914973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
120204300392240000600726025120100100120000100120000500960000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
120204300392240000720041025120100100120000100120000500960000030020317533004214973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
1202043092222500002700041025120100100120000100120000500960000030020317533004214973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
120204300392250000510041025120100100120000100120000500960000030020300393004014973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
1202043003922500002700410251201001001200001001200005009600000300203004030041149731515000120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040
12020430039224000000041025120100100120000100120000500960000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403094330040
120204300392250000270041025120100100120001100120000500960000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003601200001003004030040300403004030040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f373f4e51inst 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)5f60696b6d6edispatch 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)9fa0a1a6a7a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430681225000000046025120010101200171012000050960000113002003003930039166773150191200102012000020360000300393092211120021109101012000010000000007522311716211773003601550120000103009030040300403009030040
120024300392250000000470251200101012000110120000509900001131091030039300911499671501912001020120000203600003175030040111200211091010120000100000000075223118162117730036015516120000103004030040300403004030040
1200243003922500001981081767025120010101200001012000050990000113002103003930922149963150191200102012000020360000300393004011120021109101012000010000100007522311516211573091901550120000103004030040300403004030040
120024300392310000001746025120011101200001012000050960000113002103004030039149963150191200102012000020360000300423175011120021109101012000010000000007522311716211753003601550120000103004030040300403004030040
12002430040224000300067025120010101200001012000050960000113002033003930039149963150201200102012000020360000300393003911120021109101012000010003000007522311516211573003701550120000103004030040300403092330923
12002430040225000000067025120010101200001012000050960000113002003003930039149963159021200102012000020360000309223003911120021109101012000010000020007522311716211773003601550120000103004030040300403004030040
1200243004022500002670046025120010101200001012000050960000113002003003930039149963150491200102012000020360000309223003911120021109101012000010003000007522311716211573091901550120000103004131751300413004030041
1200243095122510100016663405251200111012001710120000509600001130021030040300401499624150191200102012000020360000300393003911120021109101012000010000000007522311516211753003701550120000103004030040300413004030040
12002430040225000000046025120010101200521012000050960000113080603094330039150163150191200102012000020360000300403003911120021109101012000010020000007522311716211753003601550120000103004030944300403004030089
1200243003922500000264046671325120011101200001012000050960000113002003009131912149963150191200102012000020360000300393057311120021109101012000010000000007522321716211753003601550120000103004030040300403004030952