Apple M1 Microarchitecture Research by Dougall Johnson

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

RSUBHN2 (8H)

Test 1: uops

Code:

  rsubhn2 v0.16b, v1.8h, v2.8h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723186125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723018125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415828951000100030003037303711100110000073116112630100030383038303830383038
1004303722091225482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372366125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723091225482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  rsubhn2 v0.16b, v1.8h, v2.8h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033a3f4e51inst 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)9fa6a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071002162229634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071002162229634100001003003830038300383003830038
102043003722501452954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
102043003722507262954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372251612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250822954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071013162229634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071212162229634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010020071012162329634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a18191e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000132529548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000291406403163329630010000103003830038300383003830038
1002430037225000000037729548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
1002430037225000000089029548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000006403163429630010000103003830038300383003830038
1002430037224000000089429548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
1002430037225000000091629548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
1002430037225000100016829548251001810100161010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329668010000103003830038300383003830038
100243003722500020006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000306403163429630010000103003830038300383003830038
1002430037225000000023829548251001010100001010000504278670130018300843008428287328767101592010000203050430037300371110021109101010000104000306603163329630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  rsubhn2 v0.16b, v0.8h, v1.8h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e1f3f4e51inst 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
10204300372250000010329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250000054329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250000020029548251010010010000100100005004277313030018300373003728265328745101002001017220030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007100161129634100001003003830038300383003830038
10204300372250000020829548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722509429548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225014729548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229700010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225065829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100136402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722508229548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  rsubhn2 v0.16b, v1.8h, v0.8h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)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)9fa1a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225961295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372258461295482510100100100001151000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037224061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250145295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000033061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300853003830038
1002430037224000000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000020006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000084295482510010101000010100005042773133001803003730083282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830227
1002430037225010000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000200046402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000010006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  rsubhn2 v0.16b, v8.8h, v9.8h
  movi v1.16b, 0
  rsubhn2 v1.16b, v8.8h, v9.8h
  movi v2.16b, 0
  rsubhn2 v2.16b, v8.8h, v9.8h
  movi v3.16b, 0
  rsubhn2 v3.16b, v8.8h, v9.8h
  movi v4.16b, 0
  rsubhn2 v4.16b, v8.8h, v9.8h
  movi v5.16b, 0
  rsubhn2 v5.16b, v8.8h, v9.8h
  movi v6.16b, 0
  rsubhn2 v6.16b, v8.8h, v9.8h
  movi v7.16b, 0
  rsubhn2 v7.16b, v8.8h, v9.8h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200901500661258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000101115161120061181600001002006520065200652006520065
1602042006415003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
1602042006415103925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010010010111116112006101600001002006520065200652006520065
1602042006415003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002013320065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
16020420064150051425801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307081e3f51inst 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)9fa8cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420086150100452780012128000012800006264000011200322005120060322800122080000202400002005120051111600211091010160000100100303229282521188200482202160000102005220052200522005220052
160024200511500006232780012128000012800006264000011200322005120051322800122080000202400002005120051111600211091010160000100100373129725411613200482201160000102005220052200612005220052
16002420051150000452780012128000012800006264000011200322005120051322800122080000202400002005120051111600211091010160000100100373126102521147200482201160000102005220052200522005220052
160024200511500004527800121280000128000062640000112004120051200513228001220800002024000020051200511116002110910101600001001003731251425221612200482401160000102005220052200522005220061
1600242005115000045278001212800001280000626400001120032200512005132280012208000020240000200512005111160021109101016000010010030312552521189200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000011200322006020051322800122080000202400002005120051111600211091010160000100100283126925211149200482202160000102005220052200522006120052
16002420060150000682780012128000012800006264000001200412005120051322800122080000202400002006020051111600211091010160000100100303128162521288200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000011200322005120060322800122080000202400002006020051111600211091010160000100100293125132522246200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000011200322005120051322800122080000202400002005120051111600211091010160000100100303121142521185200482201160000102005220052200522005220052
1600242005115000045278001212800001280000626400001120032200512005132280012208000020240000200512005111160021109101016000010010031312272521197200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  rsubhn2 v0.16b, v16.8h, v17.8h
  rsubhn2 v1.16b, v16.8h, v17.8h
  rsubhn2 v2.16b, v16.8h, v17.8h
  rsubhn2 v3.16b, v16.8h, v17.8h
  rsubhn2 v4.16b, v16.8h, v17.8h
  rsubhn2 v5.16b, v16.8h, v17.8h
  rsubhn2 v6.16b, v16.8h, v17.8h
  rsubhn2 v7.16b, v16.8h, v17.8h
  rsubhn2 v8.16b, v16.8h, v17.8h
  rsubhn2 v9.16b, v16.8h, v17.8h
  rsubhn2 v10.16b, v16.8h, v17.8h
  rsubhn2 v11.16b, v16.8h, v17.8h
  rsubhn2 v12.16b, v16.8h, v17.8h
  rsubhn2 v13.16b, v16.8h, v17.8h
  rsubhn2 v14.16b, v16.8h, v17.8h
  rsubhn2 v15.16b, v16.8h, v17.8h
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0318191e1f373f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400392990000175102516011710016001710016000050012800000400304004040039199733200071601002001600002004800004004040053111602011009910010016000010000010110116114004601600001004004140040400504004940050
16020440049299000005002516010110016000110016000050012800001400294004840039199733200071601002001600002004800004004040039111602011009910010016000010000010110116114003601600001004004040040400404017640040
160204400493000012004202516010010016001710016000050012800000400294012040039199733199981601002001600002004800004004940039111602011009910010016000010000010110116114003601600001004004040041400404004140040
1602044003930000132176042252516010010016001710016000050012800000400304004840039199733200071601002001600002004800004003940048111602011009910010016000010010010110116114004501600001004004040040400494004040041
160204400393000000174202516011710016001710016000050012800000400204003940039199733199971601002001600002004800004004940039211602011009910010016000010000010110116114003601600001004004040040400404005040049
160204400713000000183025160117100160000100160000500128000004009540039400931998513200251601002001600002004800004003940039111602011009910010016000010010010110116114004601600001004004040050400404004940040
160204400713000012005102516010010016000010016000050013199980400204004840039199733199971601002001600002004800004004840039111602011009910010016000010000010110116114003701600001004004940040400404005040041
160204400392990000174102516010110016000110016000050023989990400204003940040199733199971601002001600002004800004003940048111602011009910010016000010000010169160114003601600001004004140040400494004940040
16020440048300000005002516010110016001710016000050012800000400294004940040199733200381601002001600002004800004004840039111602011009910010016000010000010110116114003601600001004004940049400414004040041
160204400482990093004102516010010016001710016000050023989990400204003940040199733199971601002001600002004800004003940039111602011009910010016000010000010110116114004601600001004004040049400504004140041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e373f51inst 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)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)9fa1a8a9acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004929900046251600271016000010160000501280000114002004004840039199960320019160010201600002048000040039400481116002110910101600001000000100223123131621161240045155160000104004040049400404008940049
160024400483000017552516001010160000101600005023989991040029040039400481999603200281600102016000020480000400394003911160021109101016000010000001002231237162213940036155160000104004940049400494004040049
16002440048299000552516001010160017101600005012800001140020040048400391999603200191600102016000020480000400394004811160021109101016000010000001002231229162119340036155160000104004940040400494004040049
160024400393000017552516001010160000101600005023989991040029040048400391999603200281600102016000020480000400394004811160021109101016000010000001002231269162119540036155160000104004940040400494004940049
160024400393000017782516001010160017101600005023989991040029040039400481999603200281600102016000020480000400484003911160021109101016000010000001002231226162115340036155160000104004040049400404004940049
160024400483000004625160027101600171016000050239899910400200400484004819996032001916001020160000204800004003940049111600211091010160000100000010022312310162114940045155160000104004940049400404004940049
160024400483000017462516001010160000101600005023989991040029040048400481999603200281600102016000020480000400394003911160021109101016000010000001002231268162115340046155160000104004940049400494004040040
160024400483000017552516001010160000101600005023989991140029040048400391999603200191600102016000020480000400484004811160021109101016000010000001002231229162119540045155160000104004040049400404004940040
1600244003930000175525160010101600171016000050239899911400290400484003919996032002816001020160000204800004004840048111600211091010160000100000010022312451621111540045155160000104004940040400494004940049
16002440039300000522516002710160017101600005023989991040029040048400481999603200191600102016000020480000400394004811160021109101016000010000001002231245162119340045155160000104004940049400404004940049