Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLAL2 (vector, 2D)

Test 1: uops

Code:

  smlal2 v0.2d, v1.4s, v2.4s
  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)03181e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723008225392510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723008225482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001008100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073216112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlal2 v0.2d, v1.4s, v2.4s
  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)03090b1e3a3f4e51inst 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)9faccdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225005406129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225002706129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250012906129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722400006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002530037225372061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225543061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001010640216322963010000103003830038300383003830038
100243003722430061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722527061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722530061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722512061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722436061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722530061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722442061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlal2 v0.2d, v0.4s, v1.4s
  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)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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010019571021611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010013871011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010015371011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100371011611296340100001003003830038300383003830038
1020430037225000007262954825101001001000010010000500427731313001830084301802826532874510100200100002003000030037300371110201100991001001000010011471011611296340100001003003830038300383003830038
1020430037225000002512954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010011471011611296340100001003003830038300383003830038
1020430037225000002512954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010010271011611296340100001003003830038300383003830038
1020430037225000001562954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010013571011611296340100001003003830038300383003830038
1020430037225000004222954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010010571011611296340100001003003830038300383003830038
10204300372250000025129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100071001611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000441295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001176404162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001476402162229668010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010096402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001296402162229630010000103003830038300383003830038
1002430037224000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001001386402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001001116402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001446402162229630010000103003830038300383003830038
10024300372240000103295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001176402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828725287671001020100002030000300373003711100211091010100001001116402162229630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001001146402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlal2 v0.2d, v1.4s, v0.4s
  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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001004367101161129634100001003003830038300383003830038
102043003722601261295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100431147101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001003407101161129706100001003008530038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001004007101161129634100001003003830038300383003830038
10204300372250661295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100037101161129634100001003003830038300383003830038
102043003722500612954825101001071000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001003507101161129634100001003003830038300383003830038
102043008422500612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001003907101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001003707401161129634100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001004307101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100067101161129634100001003003830038300383003830038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372251061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100810640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000100960640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000100180640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010860640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000104300640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000104330640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000104600640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000104900640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000105400640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000104200640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlal2 v0.2d, v8.4s, v9.4s
  movi v1.16b, 0
  smlal2 v1.2d, v8.4s, v9.4s
  movi v2.16b, 0
  smlal2 v2.2d, v8.4s, v9.4s
  movi v3.16b, 0
  smlal2 v3.2d, v8.4s, v9.4s
  movi v4.16b, 0
  smlal2 v4.2d, v8.4s, v9.4s
  movi v5.16b, 0
  smlal2 v5.2d, v8.4s, v9.4s
  movi v6.16b, 0
  smlal2 v6.2d, v8.4s, v9.4s
  movi v7.16b, 0
  smlal2 v7.2d, v8.4s, v9.4s
  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)030b18191e3f51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009015100003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011121611200611600001002006520065200652006520065
16020420064150000393925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010001001011111611200611600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010002001011111611200611600001002006520065200652006520065
16020420064150001039159801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010001001011111611200611600001002006520065200652006520065
1602042006415100003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010003001011111611200611600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010009001011111611200611600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011111611200611600001002006520065200652006520065
16020420064150000039258010010080000100800005006400000200452006420064310580100200800002002400002006420064111602011009910010016000010001001011111611200611600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010001021011111611200611600001002006520065200652006520065
1602042006415000008125801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010002001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080918191e3f51inst 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)5f60696b6d6escheduler 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)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200711500000645258001212800001280000626400001120027020050200503228001220800002024000020046200461116002110910101600001000100333225204224620047215160000102005120051200472005120047
1600242004615000000452580012128000012800006264000011200270200502005032280012208000020240000200502005011160021109101016000010033100296224204224420047215160000102005120047200512005120051
16002420050150001101818258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001000100326114202114320043215160000102004720047200472005120051
16002420046150000004525800121280000128000062640000112002702004620046322800122080000202400002004620046111600211091010160000100114100273114202117720043215160000102004720047200472004720051
160024200461510000045258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001020100273114202114720043215160000102004720047200472004720047
160024200461500000045258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001003100273114202117720043215160000102004720047200472004720047
160024200461500000045258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001000100273116202114720043215160000102004720047200472004720051
1600242004615000401866258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001030100273113202114420043215160000102004720047200472004720047
1600242004615000000452580012128000012800006264000011200270200462004632280012208000020240000200462004611160021109101016000010042100273114202116620043215160000102004720047200472004720047
1600242004615000001287258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001000100273114202114720043215160000102004720047200472012920051

Test 6: throughput

Count: 16

Code:

  smlal2 v0.2d, v16.4s, v17.4s
  smlal2 v1.2d, v16.4s, v17.4s
  smlal2 v2.2d, v16.4s, v17.4s
  smlal2 v3.2d, v16.4s, v17.4s
  smlal2 v4.2d, v16.4s, v17.4s
  smlal2 v5.2d, v16.4s, v17.4s
  smlal2 v6.2d, v16.4s, v17.4s
  smlal2 v7.2d, v16.4s, v17.4s
  smlal2 v8.2d, v16.4s, v17.4s
  smlal2 v9.2d, v16.4s, v17.4s
  smlal2 v10.2d, v16.4s, v17.4s
  smlal2 v11.2d, v16.4s, v17.4s
  smlal2 v12.2d, v16.4s, v17.4s
  smlal2 v13.2d, v16.4s, v17.4s
  smlal2 v14.2d, v16.4s, v17.4s
  smlal2 v15.2d, v16.4s, v17.4s
  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)0308090b1e1f373f51inst 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)9fa0a1a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044007330000000041251601001001600001001600005001280000140020400394003919973319998160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004005040050400404004040040
1602044003930000000141251601001001600001001600005001280000140020400394003919973320007160100200160000200480000400394004911160201100991001001600001000000010110116114003601600001004005040050400504005040040
1602044003930000000062251601001001600001001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114004601600001004004040040400404004040040
16020440039300000001872251601001001600001001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114004501600001004004040040400404004040040
1602044004930000000041251601001001600001001600005001280000140020400494004919973319997160100200160000200480000400394003911160201100991001001600001000000110110116114003601600001004004040040400404004040040
1602044004030000000041251601001001600001001600005002438865140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004004040040400404004040040
1602044003930000000041251601001001600001001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114004601600001004004040040400404004040040
1602044003930000000062251601001001600001001600005001280000140020400394009019973320007160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004004040040400404004040040
1602044003930000000041251601001001600001001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110116114003601600001004005040050400504005040050
16020440039300000000231251601001001600001001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001002000010110116114003701600001004004040040400404004040050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373a3f51inst 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)9fa0a6a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400483000005525160027101600171016000050239899901400294003940039199963200281600102016000020480000400394004811160021109101016000010000001002231128162112525400360155160000104004940040400494004040040
1600244003930001705525160027101600011016000050128000021400304004840040199963200291600102016000020480000400494004811160021109101016000010000001002231125162112525400450155160000104005040040400404004040040
16002440039300017061625160027101600011016000050131999811400214003940040199963200191600102016000020480000400494003911160021109101016000010002301002231125162111225400360155160000104004940049400404004940040
160024400393000104725160010101600001016000050131999811400294003940039199963200191600102016000020480000400394004811160021109101016000010000001002231125162212525400360155160000104004040049400404004040049
160024400483000005525160010101600171016000050128000001400304003940039199963200191600102016000020480000400484003911160021109101016000010000001002231125162111225400450155160000104004040049400404004040040
160024400393000005525160010101600001016000050128000011400214004840048199963200281600102016000020480000400484003911160021109101016000010000001002231125164111025400370155160000104004940040400494004040041
1600244003930000047251600101016000110160000502398999114002040048400391999632001916001020160000204800004004840039511600211091010160000100000010024622121642225134003703012160000104005040050400404004040040
160024400393000015225160027101600171016000050239899911400304004940039199963200281600102016000020480000400394004811160021109101016000010000001002231125162112510400450155160000104004040049400414004040040
160024400483000104661160027101600171016000050239899911400294004840039199963200281600102016000020480000400484003911160021109101016000010000001002231112162111025400450155160000104005040041400404004040040
1600244003930001704625160011101600001016000050239899911400304004840039199963200291600102016000020480000400484004911160021109101016000010000001002231125162111225400360155160000104004140049400404004040040