Apple M1 Microarchitecture Research by Dougall Johnson

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

UMLSL2 (vector, 4S)

Test 1: uops

Code:

  umlsl2 v0.4s, 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612548251000100010003983131301830373037241532895100010003000303730371110011000100073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100080073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100080073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303722082254825100010001000398313130183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303722061254825100010001000398313030183037308524153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100010073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  umlsl2 v0.4s, 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)0307080a0b1e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)6061696d6edispatch stall (70)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)9fa6a7a8acbranch mispredict (cb)cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225101018125429548251010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010000000713103165529634100001003003830038300383003830038
102043003722510100172929548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000490713106165529634100001003003830038300383003830038
10204300372251011016429548251010010010000100100005004278079003001830037300372826532874510100200100002003000030037300371110201100991001001000010000200713105163529634100001003003830038300383003830038
102043003722510100134929548451010010410000102100005004277313003001830037300852826532874510100200100002003000030037300371110201100991001001000010000000712104165429634100001003003830038300383003830038
10204300372251010016429548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000000713103164429634100001003003830038300383003830038
10204300372251010016429548251010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010000000713105165529634100001003003830038300383003830038
10204300372241010016429548251010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010030030716103165529634100001003003830038300383003830038
10204300372251010016429548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000300713103163529634100001003003830038300383003830038
10204300372251010026429548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000000713103164529634100001003003830038300383003830038
10204300372331010357176029548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000300712106165529634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)5e60696b6d6edispatch 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773130030018030037300372828732876710010201000020300003003730037111002110910101000010000906403162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130030018030037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130030018030037300372828732876710010201000020300003003730037111002110910101000010002006403162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130030018030037300372828732876710010201000020300003003730037111002110910101000010003906402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130030018030037300372828732876710010201000020300003003730037111002110910101000010001306403162229630010000103003830038300383008530038
100243003722500000061295482510010101000010100005042773130030018030037300372828732876710010201000020300003003730037111002110910101000010004555006403162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130030018030037300372828732876710010201000020300003003730037111002110910101000010002006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731300300180300373003728287328767100102010000203000030037300371110021109101010000100034006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731300300180300373003728287328767100102010000203000030037300371110021109101010000100038006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731300300180300373003728287328767100102010000203000030037300371110021109101010000100035006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  umlsl2 v0.4s, 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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722508742954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722508192954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003008630038300383003830038
1020430037225122122954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000171021622296340100001003003830038300383003830038
102043003722501242954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296348100001003003830038300383003830038
102043003722501032954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722501032954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722501472954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722401452954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722401722954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722401522954825101001001000010010000500427731303001830037300372826532874510100200101762003000030037300371110201100991001001000010060071021622296340100001003003830038300383003830038

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)9fa1a8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722515961295482510010121000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100006042773131300183003730037282873287671001020100002030000300373003711100211091010100001002030640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001220100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010101485042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  umlsl2 v0.4s, 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)033f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722525429548251010010010000100100005004277313030018300373003728272728740101002001000820030024300373003711102011009910010010000100001117410160029646100001003003830038300383003830038
102043003722517029548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722521229548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722519129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100090007101161129634100001003003830038300383003830038
102043003722516829548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722517029548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372258429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722525429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722523329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372258429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500333295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006404166629630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006406165529630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006405165629630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006406166629630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006405165429630010000103003830038300383003830038
10024300372250084295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006406166629630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006406166529630010000103003830038300383003830038
100243003722500191295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006405165529630010000103003830038300383003830038
100243003722500170295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006406166529630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006406165629630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  umlsl2 v0.4s, v8.8h, v9.8h
  movi v1.16b, 0
  umlsl2 v1.4s, v8.8h, v9.8h
  movi v2.16b, 0
  umlsl2 v2.4s, v8.8h, v9.8h
  movi v3.16b, 0
  umlsl2 v3.4s, v8.8h, v9.8h
  movi v4.16b, 0
  umlsl2 v4.4s, v8.8h, v9.8h
  movi v5.16b, 0
  umlsl2 v5.4s, v8.8h, v9.8h
  movi v6.16b, 0
  umlsl2 v6.4s, v8.8h, v9.8h
  movi v7.16b, 0
  umlsl2 v7.4s, 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)0307080a0b181e3f51inst 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)9fa1a8acc2cfd0d2icache miss (d3)d5d6dbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500000003925801001008000010080000500640000012004520064200643228010020080000200240000200642006411160201100991001001600001000000101120002160222006101600001002006520065200652006520065
160204200641510000003965801001008000010080000500640000002004520064200643228012420080000200240000200642006411160201100991001001600001000000101120002160222006101600001002006520065200652006520065
160204200641500000003925801001008000010080000500640000012004520064200643228010020080000200240000200642006411160201100991001001600001000000101120005160222006101600001002006520065200652006520065
160204200641500000003925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000000101123002160222006101600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000002004520064200643228010020080000200240000201342006411160201100991001001600001000000101120002160222006101600001002006520065200652006520065
1602042006415000000039258010012480000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011200021602220061211600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000000101120002160332006101600001002006520065200652006520065
160204200641500000003925801001008000010080000500640000002004520064200643228010020080000200240000201492006411160201100991001001600001000000101120004250222006101600001002006520065200652006520065
160204200641500000003925801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001000000101140002160222006101600001002006520065200652006520065
160204200641500000003925801001008000010080000500640000012004520064200643228010020080000200240000200642006411160201100991001001600001000000101180012160222006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a1e3a3f51inst 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)5f6061696b6d6escheduler 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)9faccfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420073150000452780012128000012800006264000011020032020051200513228001220800002024000020051200511116002110910101600001001004831114252112714200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000010020032020051200513228001220802092024000020051200511116002110910101600001001004831125252111325200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000011520032020051200513228001220800002024000020051200511116002110910101600001001005084125252112531200482201160000102005220052200522005220052
160024200511500004527800121280000128000062640000105200320200602005132280012208000020240000200602006011160021109101016000010010039114225344221324200572402160000102006120061200612006120061
160024200601500005129800121280000128000062640000015200410200602006032280012208000020240000200512005111160021109101016000010010051113225344222525200572402160000102006120061200612006120061
16002420060150000452780012128000012800006264000010520032020051200513228001220800002024000020051200511116002110910101600001001004832125252112525200482201160000102005220052200522005220052
160024200511500005129800121280000128000062640000015200410200602006032280012208000020240000200512005111160021109101016000010010051113225344221125200572402160000102006120061200612006120061
16002420060150000502780012128000012800006264000011020032320132200513228001220800002024000020051200511116002110910101600001001004831125252111325200482201160000102005220052200522005220052
160024200511500004527800121280000128000062640000105200320200512005132280012208000020240000200512005111160021109101016000010010034113125342211125200572402160000102005220061200522006120052
16002420051150000662780012128000012800006264000011020032020051200513228001220800002024000020051200601116002110910101600001001003481111252111325200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  umlsl2 v0.4s, v16.8h, v17.8h
  umlsl2 v1.4s, v16.8h, v17.8h
  umlsl2 v2.4s, v16.8h, v17.8h
  umlsl2 v3.4s, v16.8h, v17.8h
  umlsl2 v4.4s, v16.8h, v17.8h
  umlsl2 v5.4s, v16.8h, v17.8h
  umlsl2 v6.4s, v16.8h, v17.8h
  umlsl2 v7.4s, v16.8h, v17.8h
  umlsl2 v8.4s, v16.8h, v17.8h
  umlsl2 v9.4s, v16.8h, v17.8h
  umlsl2 v10.4s, v16.8h, v17.8h
  umlsl2 v11.4s, v16.8h, v17.8h
  umlsl2 v12.4s, v16.8h, v17.8h
  umlsl2 v13.4s, v16.8h, v17.8h
  umlsl2 v14.4s, v16.8h, v17.8h
  umlsl2 v15.4s, 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)0307080a0b18191e1f373a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)6061696d6edispatch stall (70)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)9fa1a6a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400513000000008401070702516011710016001710016000050023989991540021400394004019973319997160100200160000200480000400484003911160201100991001001600001000000001011001116114003601600001004004040040400404004040040
160204400392990000006000664502516010010016000010016000050013200000040021400404003919973320006160100200160000200480000400394004011160201100991001001600001000000601011000116114003601600001004004040041400404004140040
16020440048300000000360005002516010110016000010016000050012800000040021400404004019973320029160100200160000200480000400494004811160201100991001001600001000000001011000116114003701600001004005040049400494004040040
16020440039300000000390104102516011710016000110016000050012800000040021400494004019973320007160100200160000200480000400394004011160201100991001001600001000000001011000116114003601600001004004040041400404005040041
16020440048300000000210104102516010010016001710016000050023990270040020400404004019973319997160100200160000200480000400394003911160201100991001001600001000000001011000116114003701600001004004140040400504004040050
16020440048300000000360005102516011710016000010016000050013200000040020400394004919973320007160100200160000200480000400394004011160201100991001001600001000000001011000116114003701600001004004140040400414004040041
16020440039299000000180105002516010010016001710016000050053871880040021400394003919973319997160100200160000200480000400404004911160201100991001001600001000200001011000116114004601600001004004940041400414004040595
1602044060730400119101506616145119155023316118512516062612416120462316109111540608403094060420167332032116136420216044520048395740645405521111602011009910010016000010040103148410293001114384062101600001004005040040400494004040041
160204400403000000001689105618701353126251161471122161296121161351661156333400406364072440797201825620399161207204161260204485229407864075613116020110099100100160000100002065350103340031514540735241600001004105441006408774062140733
1602044102031921111189396161804202516010110016001710016000050012800000040030400404004020000662046916236920016193720448523540919409441411602011009910010016000010000000010110500116164004501600001004009140040400404005040040

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)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)9fa8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004930075600552516001010160017101600005012800001140020400394004019996032002916001020160000204800004004840039111600211091010160000100000100223116162117640036155160000104004040041400404004940040
1600244003930048900462516001110160017101600005013200001140020400394004019996032002816001020160000204800004003940039111600211091010160000100000100223115162115640036155160000104009040040400404004040040
16002440048299525170462516001010160000101600005023989991140020400394004819996032001916001020160000204800004003940048111600211091010160000100000100223116162116540036155160000104004040049400494005040040
160024400392993910552516002710160000101600005023989991140020400394004819996032013716001020160000204800004003940039111600211091010160000100000100223115162117640045155160000104004040040400494004040049
160024400392999000462516001010160000101600005023989991140020400394003919996032001916001020160000204800004003940039111600211091010160000100000100223119162115840045155160000104004940040400504004040040
1600244004930062700552516001010160000101600005023989991140020400394004819996032002816001020160000204800004004840039111600211091010160000100000100223117162117640036155160000104004040049400494005040040
16002440039300486170552516001010160017101600005012800001140020400394004819996032002816001020160000204800004003940039111600211091010160000103000100223115162116840036155160000104004040040400404004940040
1600244003930068700462516002710160017101600005012800001140020400394003919996032004816001020160000204800004004840039111600211091010160000100000100223217162115540036155160000104004940040400494004040040
16002440048300660170552516001010160001101600005012800001140020400484003919996032019216001020160000204800004004840039111600211091010160000100000100223216162117740036155160000104004040040400404004140040
1600244004030066900472516002710160000101600005023990271140020400394004019996032002816001020160000204800004004940039111600211091010160000100000100223117162117740036155160000104004140040400404004040040