Apple M1 Microarchitecture Research by Dougall Johnson

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

RSUBHN2 (2D)

Test 1: uops

Code:

  rsubhn2 v0.4s, v1.2d, v2.2d
  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)031e3a3f4e51inst 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
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
1004303723306125482510001000100039831313018303730372415328951000100030003037303711100110000073516662630100030383038303830383038
1004303723006125482510001005100039831313018303730372415328951000100030003037303711100110000073616552630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
10043037230033625482510001000100039831313018303730372415328951000100030003037303711100110000073616652630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000095616662630100030383038303830383038
10043037230025225482510001000100039831313018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
10043037221806125482510001000100039831313018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037312111100110000073616662630100030383038303830383038

Test 2: Latency 1->1

Code:

  rsubhn2 v0.4s, v1.2d, v2.2d
  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)030b1e1f3a3f4e51inst 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)9fa6a8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071003163429634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071003163429634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071214163329634100001003003830084300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071013161329634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100003071013164329634100001003003830038300383013330038
1020430037225000082295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000161295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000071013163329634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa1a6acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006404162229630010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
100243003722500004412954825100101010000101014950427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006404163329630010000103003830038300383003830038
10024300372360000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006403164229630010000103003830038300383003830038
100243003722500005362954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006403163229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402163229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006403163229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010234125206633163329630110000103003830038300383003830085
1002430037224121561049662954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402163329630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  rsubhn2 v0.4s, v0.2d, v1.2d
  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)0307080a0b18191e1f3a3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000000184295482510100100100001251000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011655296340100001003003830038300383003830038
102043003722500000000161295482510100100100001001000062642773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003008530038300383003830038
102043003722500000000161295482510100100100001001000050042773133001830037300372826572874510253200100002003000030037300371110201100991001001000010000100071011611296340100001003003830038300383003830038
102043003722500000000061295482510125100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037224000000000536295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000000061295482510100107100001251000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

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)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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006403165529630010000103003830038300383003830038
100243003722500000006129548251001010100001010447504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006406165629630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405165529630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002031956300373003711100211091010100001000000000006406166529630110000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006406166529630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405165529630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405166629630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405165529630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030990300373003711100211091010100001022000000006405164429630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000000006405165429630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  rsubhn2 v0.4s, v1.2d, v0.2d
  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)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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000018929548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100010671021611296340100001003003830132300383003830038
102043003722500003526129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071031611296340100001003003830038300383003830038
10204300372250001206129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003741102011009910010010000100000073211611296340100001003003830038300383003830038
1020430037225030006129548251010010010000100100005004277313030018300373003728265328745101002041000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383022730038
10204300372240000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710116112963421100001003003830038300383003830038
10204300372250000022729548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100010371011611296340100001003003830038300383003830038
1020430037225011006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373008511102011009910010010000100012071011611296340100001003003830038300383003830038

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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430179225061295483610010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630110000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001001146402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225061295488410010101000010100005042773133001830037300372828732876710010201000020300003013230037111002110910101000010106402162229630010000103003830038300383003830038
10024300372251261295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  rsubhn2 v0.4s, v8.2d, v9.2d
  movi v1.16b, 0
  rsubhn2 v1.4s, v8.2d, v9.2d
  movi v2.16b, 0
  rsubhn2 v2.4s, v8.2d, v9.2d
  movi v3.16b, 0
  rsubhn2 v3.4s, v8.2d, v9.2d
  movi v4.16b, 0
  rsubhn2 v4.4s, v8.2d, v9.2d
  movi v5.16b, 0
  rsubhn2 v5.4s, v8.2d, v9.2d
  movi v6.16b, 0
  rsubhn2 v6.4s, v8.2d, v9.2d
  movi v7.16b, 0
  rsubhn2 v7.4s, v8.2d, v9.2d
  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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420065150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011231622200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
160204200641501983925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010001501011221622200611600001002006520065200652006520065
1602042006415066149258021510080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
16020420064150060258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
160204200641500102258010010080000100800005006400000200452006420064322801002008010520024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
16020420064150062258010010080000100800005006400001200452006420064322801002008000020024037220064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
160204200641500102258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
160204200641500102258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065

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)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)9fa8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200601502466258001212800001280000626400001120027200462004632280012208000020240000200502005011160021109101016000010000100356221220211121020043215160000102004720047200472004720047
16002420046150045258001212800001280000626400000120027200462005032280012208000020240000200502005011160021109101016000010000100336111020211131220043215160000102004720047200472004720047
160024200461501545258001212800001280000626400001120027200502005032280012208000020240000320222004611160021109101016000010000100343121220412121220047215160000102005120051200512005120141
160024200501501245258001212800001280000626400001020027200462004632280012208000020240000200462004611160021109101016000010000100333111320221131320047215160000102005120051200512005120051
160024200501501533025800121280000128000062640000112002720046200463228001220800002024000020046200501116002110910101600001000010036311102021113920043215160000102004720047200472004720047
16002420046150045258001212800001280000626400001120027200462004632280012208000020240000200502005011160021109101016000010000100353111154211131120043215160000102004720047200472004720047
1600242004615010245258001212800001280000626400001120027200462004632280012208000020240000200462004611160021109101016000010160100333111020211111220043215160000102004720047201292004720047
160024200461508145258001212800001280000626400001120027200462004632280326208000020240000200462004611160021109101016000010000100363111120211111020043215160000102004720047200552004720047
16002420046150964525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000010035311102021191220043215160000102004720047200472004720047
160024200461501553258001212800001280000626400001120027200462004632280012208000020240000200462004611160021109101016000010000100363111120211111220043215160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  rsubhn2 v0.4s, v16.2d, v17.2d
  rsubhn2 v1.4s, v16.2d, v17.2d
  rsubhn2 v2.4s, v16.2d, v17.2d
  rsubhn2 v3.4s, v16.2d, v17.2d
  rsubhn2 v4.4s, v16.2d, v17.2d
  rsubhn2 v5.4s, v16.2d, v17.2d
  rsubhn2 v6.4s, v16.2d, v17.2d
  rsubhn2 v7.4s, v16.2d, v17.2d
  rsubhn2 v8.4s, v16.2d, v17.2d
  rsubhn2 v9.4s, v16.2d, v17.2d
  rsubhn2 v10.4s, v16.2d, v17.2d
  rsubhn2 v11.4s, v16.2d, v17.2d
  rsubhn2 v12.4s, v16.2d, v17.2d
  rsubhn2 v13.4s, v16.2d, v17.2d
  rsubhn2 v14.4s, v16.2d, v17.2d
  rsubhn2 v15.4s, v16.2d, v17.2d
  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)03070a0b1e1f373a3f51inst 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)9fa7a8acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400593001108100251251601001001600001001600005002399082040020400394004819973319998160100200160000200480000400394004811160201100991001001600001000000001011415161212400361600001004004940040400404004940049
16020440039300110000251251601171001600001001600005002398999040020400394004819973319997160100200160000200480000400394003911160201100991001001600001000200001011414161415400361600001004004940040400404004940049
16020440039300110000251251601001001600171001600005001280000040020400394004819973319997160100200160000200480000400394003911160201100991001001600001000000001011412161512400361600001004004040040400404004040040
16020440048300110000251251601001001600181001600005001280000040020400484003919973319997160100200160000200480000400484003911160201100991001001600001000002001011414161314400361600001004004940040400404004040040
16020440039300110000251251601001001600001001600005001280000040020400394004819973319997160100200160000200480000400494003911160201100991001001600001000000001011414161515400361600001004004040040400404004040040
16020440048300110000260251601171001600001001600005001319999040020400394004819973319997160100200160000200480000400394003911160201100991001001600001000030001011414161412400361600001004004040040400404004040049
16020440039300110000251251601001001600001001600005001280000040020400394003919973320007160100200160000200480000400394003911160201100991001001600001000000001011413161611400361600001004004940040400404009940040
1602044003930011000025125160100100160000100160000500128000004002040039400391997331999716010020016000020048000040039400391116020110099100100160000100000000101147161413400361600001004004040040400404004040040
1602044003930011000026025160100100160000100160000500128000004002040039400391997331999716010020016000020048000040039400391116020110099100100160000100000000101141516613400361600001004004040040400404004940040
16020440039299110000251251601001001600011001600005001280000040020400394004819973319997160100200160000200480000400394003911160201100991001001600001000000101011412161415400361600001004004040040400494004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f373f51inst 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)9fa8acc2c5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440040300000174625160010101600001016000050128000011040020400394003919996320019160010201600002048000040039400481116002110910101600001000011002383191621172140036206160000104004040049400404004140049
160024400403000001771125160010101600171016000050128000011540020400394003919996320019160010201600002048000040039400481116002110910101600001000001002384171621192140045206160000104004040040400494004040049
160024400393000001746251600111016000010160000501280000115400204003940039199963200191600102016000020480000400394003911160021109101016000010000010023842211621172140045209160000104004940040400414004040040
160024400483000000562516001010160000101600005012800001154002040049400491999632001916001020160000204800004003940039111600211091010160000100000100238412116211212140036209160000104004140040400414004040040
160024400393000901746251600111016000010160000501280000115400204004040049199963200201600102016000020480000400394004811160021109101016000010000010023841211621121940045206160000104004940040400404004940049
160024400393000001747251600271016001710160000501280000115400294004040039199963200191600102016000020480000400484003911160021109101016000010000010023841211621121940045207160000104004940040400504004040040
160024400483000000462516002710160017101600005023990271154002040040400491999632002916001020160000204800004003940040111600211091010160000100000100238412116211212140037209160000104004040041400504004040040
1600244003930000017462516001010160017101600005013199981154003040040400491999632001916001020160000204800004003940039111600211091010160000100000100238412117211212140037206160000104004040040400404004140041
160024400393000000552516001010160017101600005023989991154002140039400481999632002916001020160000204800004003940039111600211091010160000100000100238412116211212140036209160000104004040049400404004940049
16002440048300060046251600101016000010160000502398999115402064003940048199963200281600102016000020480000400484003911160021109101016000010000010023841201621121940036209160000104004040040400404004140040