Apple M1 Microarchitecture Research by Dougall Johnson

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

SABAL (vector, 8H)

Test 1: uops

Code:

  sabal v0.8h, v1.8b, v2.8b
  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)0308191e1f3f4e51inst 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
100430372200006125482510001000100039831313018303730372415328951000100030003037303711100110003073116112630100030383038303830383038
1004303722000011025482510001000100039831313018303730372415328951000100030003037303711100110008373116112630100030383038303830383038
100430372300006125482510001000100039831313018303730372415328951000100030003037303711100110002373116112630100030383038303830383038
100430372300006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230000192254825100010001000398313130183037303724153289510001000300030373037111001100001573116112630100030383038303830383038
100430372200008425482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372300006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372300006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722000011025482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372300006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sabal v0.8h, v1.8b, v2.8b
  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)030b18191e3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000029202954825101001001000010010596500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071031622296340100001003003830038300383003830038
10204300372240009612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
10204300372250300612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
102043003722500007262954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037301791110201100991001001000010000000071021622296340100001003003830038300383003830038
102043003722500002732954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010040000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071021622296340100001003003830038300383003830038
1020430037225000061295481031010010010000100100005004277313030018300373003728265202874510100200100002003000030037300371110201100991001001000010000000071021623296340100001003003830038300383003830038
10204300372250000612954825101001061000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000003071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3a3f4e51inst 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)9fa0a1a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640916972963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000020640816872963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640816872963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640724882963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640816872963010000103003830038300383003830038
100243003722501200726295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640816882963010000103003830217300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010220000640716792963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640816872963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640716782963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010200000640716782963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sabal v0.8h, v0.8b, v1.8b
  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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000307101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500103295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372256061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722501891295482510010101000010100005042773133001830037300372828732876710010201016720300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002210910101000010000640316332963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sabal v0.8h, v1.8b, v0.8b
  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)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)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030084300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722507129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000107102162229634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225451032954865100181010000101000050427731303012603003730084282873287671001020101632030000300373003711100211091010100001010640216132963010000103003830038300383003830038
10024300372259612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001013640216222963010000103003830038300383003830038
1002430037224121032954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001010640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001022100002030000300373003741100211091010100001023640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730084282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001006640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002030000301783017941100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001833003730037282873287671001020100002030000300373003711100211091010100001000640316322963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sabal v0.8h, v8.8b, v9.8b
  movi v1.16b, 0
  sabal v1.8h, v8.8b, v9.8b
  movi v2.16b, 0
  sabal v2.8h, v8.8b, v9.8b
  movi v3.16b, 0
  sabal v3.8h, v8.8b, v9.8b
  movi v4.16b, 0
  sabal v4.8h, v8.8b, v9.8b
  movi v5.16b, 0
  sabal v5.8h, v8.8b, v9.8b
  movi v6.16b, 0
  sabal v6.8h, v8.8b, v9.8b
  movi v7.16b, 0
  sabal v7.8h, v8.8b, v9.8b
  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)9fa8a9branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200881510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011321633200611600001002006520065200652006520065
1602042006415008882580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001201011331633200611600001002006520065200652006520065
1602042006415008192580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011351633200611600001002006520065200652006520065
1602042006415009412580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011321633200611600001002006520065200652006520065
1602042006415501902580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011351633200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011351633200611600001002006520065200652006520065
1602042006415008612580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001002001011341633200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228022820080000200240000200642006411160201100991001001600001000001011251633200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011321632200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001011331633200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)5f6061696d6escheduler 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)9fa0a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200561500005125800121280000128000062640000015200312004620046322800122080000202400002004620046111600211091010160000100000101361431132041110720043215160000102004720047200472004720047
160024200461500004525800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100000101181421102021110720043215160000102004720047200472004720047
16002420046150000452580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010200010138142182021110720043215160000102004720047200472004720047
1600242004615000052025800121280000128000062640000115200272004620046274380012208000020240000200462004611160021109101016000010000010130142172021171020043215160000102004720047200472005120047
160024200461500004525800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100100101341421102021210720043215160000102005120047200472004720047
160024200461500004525800121280000128000062640000115200272004620046322800122080000202400002005020046111600211091010160000100000101281721102021171020043230160000102005120051200472005120051
160024200501500004525800121280000128000062640000015200312004620293322801162080000202400002028820125211600211091010160000100100101291722102042110720047215160000102005120047200472004720047
160024200461503004525800121280000128000062640000115200272004620046386800122080000202400002004620046111600211091010160000100000101281442102041110720043230160000102005120047200472005120047
16002420046150000512580012128000012800006264000011520027200462004632280012208000020240000200462004621160021109101016000010000410158203272421171020043215160000102004720047200472005120047
16002420046150000452580012128000012800006264000001520027200462004632280012208000020240000200462004611160021109101016000010000010118144172041171020043215160000102005120051200472005120047

Test 6: throughput

Count: 16

Code:

  sabal v0.8h, v16.8b, v17.8b
  sabal v1.8h, v16.8b, v17.8b
  sabal v2.8h, v16.8b, v17.8b
  sabal v3.8h, v16.8b, v17.8b
  sabal v4.8h, v16.8b, v17.8b
  sabal v5.8h, v16.8b, v17.8b
  sabal v6.8h, v16.8b, v17.8b
  sabal v7.8h, v16.8b, v17.8b
  sabal v8.8h, v16.8b, v17.8b
  sabal v9.8h, v16.8b, v17.8b
  sabal v10.8h, v16.8b, v17.8b
  sabal v11.8h, v16.8b, v17.8b
  sabal v12.8h, v16.8b, v17.8b
  sabal v13.8h, v16.8b, v17.8b
  sabal v14.8h, v16.8b, v17.8b
  sabal v15.8h, v16.8b, v17.8b
  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)030818191e373f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044005830000001412516010010016000010016000050012800000400204003940039199733199971601002001600002004800004004940049111602011009910010016000010000010110116114003601600001004004040049400404004040040
1602044003929900000502516011710016001710016000050023990270400204003940048199733199971601002001600002004800004003940039111602011009910010016000010000010110116114004501600001004004940049400494004040049
1602044004030000000412516010010016001710016000050012800000400204004840039199733199971601002001600002004800004003940039111602011009910010016000010000010110116114004601600001004004940049400404004040049
1602044004830000000412516011710016000010016000050012800000400204003940039199733200061601002001600002004800004003940048111602011009910010016000010000010110116114003601600001004004940049400404005040164
1602044003930001101753464160117100160000100160000500239908214002040040400391997312200941602232001600002004800004003940039311602011009910010016000010003010110116114004501600001004004040040400494004040049
16020440039300000120412516011710016001810016000050023989991400294003940049199733199971601002001600002004800004003940049111602011009910010016000010000010110116114003601600001004004040040400404004940040
16020440039300000017412516010010016001710016000050023989991400204004840039199733200061602172001600002004800004003940049111602011009910010016000010000010110116114004501600001004004040040400494004040049
1602044004831000000412516011710016000010016000050023989991400204004840039199733199971601002001600002004800004003940039111602011009910010016000010003010110116114003601600001004004040049400504004040049
1602044003930000000412516010010016000010016000050012800001400204003940048199733199971601002001600002004800004004840039111602011009910010016000010000010110116114003601600001004004040049400494004940040
16020440048299000017412516011710016000010016000050023989991400294003940039199733199971601002001600002004800004003940039111602011009910010016000010000010110116114003601600001004005040040400404004940040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373f4e51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004830090460251600101016000010160000501280000115400204003940039199963200201600102016000020480000400394004811160021109101016000010001002282191641134400450206160000104004940040400494004040049
16002440048299002210251600101016000010160000501280000115400204004840071199963200281600102016000020480000400394003911160021109101016000010001002284141621143400450206160000104007240049400404004040040
160024400713000046025160010101600001016000050538718811540020400484007119996320019160010201600002048000040039400391116002110910101600001049010024852416422434003602012160000104004040040400404004940040
1600244003930000520251600101016000010160000501280000015400204003940048199963200191600102016000020480000400394003911160021109101016000010001002284141621134400450206160000104007240049400404004040072
16002440039300005302516001010160000101600005023989990154002040039400391999632001916001020160000204800004003940048111600211091010160000100010024114241642234400360209160000104004040072400404007240040
16002440071300005202516001110160000101600005012800000154002040048400711999632001916001020160000204800004003940048111600211091010160000100010022114231621144400680409160000104007240040400404004040040
1600244003930000460251600101016001710160000501280000115400294003940039200023200511600102016000020480000400484004011160021109101016000010001002284231621134400360206160000104004040040400404004040040
1600244003930000670251600271016000010160000501280000115400204003940048199963200191600102016000020480420400484004811160021109101016000010001002484231621134400360206160000104004040040400494004040040
160024400392990614602516002710160000101600005012800001154002040048400391999632001916011020160000204800004003940039111600211091010160000100010022114131621134400360406160000104004040040400724004940040
16002440039300017550251600101016000010160000501280000115400204003940039200023200191600102016000020480000400484007111160021109101016000010001002284131622144400370209160000104007240040400724004940049