Apple M1 Microarchitecture Research by Dougall Johnson

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

SDOT (vector, 8B)

Test 1: uops

Code:

  sdot v0.2s, 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)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
100430372308225482510001000100039831313018303730372415328951000100030003037303711100110000073216112630100030383038303830383038
10043037230126254825100010001000398313130183037303724153289510001000300030373037111001100001273116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723216125482510001000100039831313018303730372415328951000100030003037303711100110002073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372208225482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000116830003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sdot v0.2s, 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)03080b181e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500018006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000100071003162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071002162229634100001003003830038300383003830038
10204300372260100006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000303071012162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313300183003730086282653287451010020010000200300003003730037111020110099100100100001000200700071212162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071012162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000100071012162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071012162229634100001003003830038300383003830038
10204300372240000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000100071012162229634100001003003830038300383003830038
10204300372250000006129548251013610010000100100005224277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000200071012162229634100001003003830038300383003830038
10204300372250000016129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000100071012162229634100001003003830038300383003830038

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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100023640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000640316322963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300180300373003728292328767100102010000203000030037300371110021109101010000100010640216222963010000103003830038300383003830038
10024300372250346295482510010101000010100005042773133001803003730037282873287671001020100002030000300373003711100211091010100001000320640216222963010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000640216232963010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100040640216322969510000103003830038300383003830038
100243003722506129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225072629548251001010100081010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100033640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sdot v0.2s, 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)03090b18191e3f4e51inst 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)9fa6a8a9acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500001216629548251015110310000107100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100092280800710116212963417100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300842826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010005000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000500120071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612951225101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

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)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225045929548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010006403162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010096402162229630010000103003830038300383003830038
1002430037225010329548251001010100001010000504277313130054030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225014929548251001010100001010000504277313030018330037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010166402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225021229548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sdot v0.2s, 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)03081e3a3f4e51inst 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)9fa0a1a6a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500010329548251010010010000100100005004277313130054300373003728265328745101002001000020030000300373003711102011009910010010000100000000071021611296340100001003003830038300383003830038
10204300372290006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011612296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000100071011612296340100001003003830038300383003830038
10204300372250006129548441010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000060071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e1f3f4e51inst 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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640616222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722400006129548251001010100001010000504277313130018300373018128287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830081300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722400006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225002406129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sdot v0.2s, v8.8b, v9.8b
  movi v1.16b, 0
  sdot v1.2s, v8.8b, v9.8b
  movi v2.16b, 0
  sdot v2.2s, v8.8b, v9.8b
  movi v3.16b, 0
  sdot v3.2s, v8.8b, v9.8b
  movi v4.16b, 0
  sdot v4.2s, v8.8b, v9.8b
  movi v5.16b, 0
  sdot v5.2s, v8.8b, v9.8b
  movi v6.16b, 0
  sdot v6.2s, v8.8b, v9.8b
  movi v7.16b, 0
  sdot v7.2s, 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)030408181e3f51inst 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)60696d6e74scheduler 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009115010003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000001011131611200611600001002006520065200652006520065
160204200641500002646025801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000001011121611200611600001002006520065200652006520065
1602042006415100003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000031011121611200611600001002006520065200652006520065
1602042006415100003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000001011121611200611600001002006520065200652013320065
1602042006415000003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000201011121611200611600001002006520065200652006520065
16020420064150000039258010010080000100800005006400001200452006420064032280100200800002002400002006420064111602011009910010016000010044001011111611200611600001002006520065200652006520065
1602042006415100003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641510002948825801001048010410080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520131

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e3f51inst 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)9fa6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200811560000452780012128000012800006264000011520233200512005132280012208000020240000200512005111160021109101016000010000100308612025211176200482201160000102005220052200522005220052
16002420051150000045278001212800001280000626400000152024120051200513228001220800002024000020051200511116002110910101600001000010040311626221616200482201160000102005220052200522005220052
160024200511510003911142780012128000012800006264000011020248200512005132280012208000020240000200512005111160021109101016000010000100408611625211166200482202160000102005220052200522005220052
1600242005115000004527800121280000128010462640000115202102005120051322800122080000202400002005120051111600211091010160000100001006586116252211616200482201160000102005220052200522005220052
160024200511500101245278001212800001280000626400001152019720051200513228001220800002024000020051200511116002110910101600001000010040861634211166200482201160000102005220052200522005220052
160024200511500000452780012128000012800006264000011520190200512005132280012208000020240000200512005111160021109101016000010000100308611625211717200482201160000102005220052200522005220052
160024200511500006512780012128000012800006264000011520206200512006032280012208000020240000200512006011160021109101016000010000100338511634211166200482201160000102005220052200522005220052
16002420132150000544527800121280000128000062640000115202152006020051322800122080000202400002005120060111600211091010160000100001004085116252111616200482201160000102005220052200522006120052
160024200511500000452780012128000012800006264000011520204200512005132280012208000020240000200512005111160021109101016000010000100408511625212166200482202160000102005220061200612005220052
16002420051150000945298001212800001280000626400001152022020051200513228001220800002024000020051200511116002110910101600001000010043115116254111616200572201160000102005220052200612005220052

Test 6: throughput

Count: 16

Code:

  sdot v0.2s, v16.8b, v17.8b
  sdot v1.2s, v16.8b, v17.8b
  sdot v2.2s, v16.8b, v17.8b
  sdot v3.2s, v16.8b, v17.8b
  sdot v4.2s, v16.8b, v17.8b
  sdot v5.2s, v16.8b, v17.8b
  sdot v6.2s, v16.8b, v17.8b
  sdot v7.2s, v16.8b, v17.8b
  sdot v8.2s, v16.8b, v17.8b
  sdot v9.2s, v16.8b, v17.8b
  sdot v10.2s, v16.8b, v17.8b
  sdot v11.2s, v16.8b, v17.8b
  sdot v12.2s, v16.8b, v17.8b
  sdot v13.2s, v16.8b, v17.8b
  sdot v14.2s, v16.8b, v17.8b
  sdot v15.2s, 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)031e1f373f51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044005930000053425160117100160001100160000500239908214002140039400391997331999716010020016000020048000040048400391116020110099100100160000100000010110116114004501600001004004940041400404004040041
1602044003930000174125160101100160001100160000500239899914002140049400391997331999716010020016000020048000040049400491116020110099100100160000100000010110116114003601600001004005040050400414005040050
1602044004030039015025160100100160017100160000500131999914002040039400491997331999716010020016000020048000040048400391116020110099100100160000100000010110116114003601600001004004940041400404004040040
160204400392990015025160100100160001100160000500239899914002040049400391997331999716010020016000020048000040040400391116020110099100100160000100000010110116114004501600001004004940040400414004140049
1602044003930000176425160100100160017100160000500181147114002040040400491997331999716010020016000020048000040039400401116020110099100100160000100000010110116114003701600001004004040041400494004040049
1602044003930000184225160117100160000100160000500131999704002040039400391997332000616010020016000020048000040039400481116020110099100100160000100000010110116114003701600001004004940049400494004940040
160204400402990014225160100100160000100160000500239899904003340040400481998331999716010020016000020048000040039400401116020110099100100160000100000010110116114003701600001004004140041400504005040049
160204400482990004125160101100160000100160000500239899914003040048400391997331999716010020016000020048000040048400391116020110099100100160000100000010110116114004501600001004004140050400504005040050
160204400402990004125160100100160000100160000500128000014002140039400481997331999716010020016000020048000040039400391116020110099100100160000100000010110116114004601600001004004940040400414004940040
1602044004830000185125160101100160018100160000500128000004002940048400391997331999816010020016000020048000040040400481116020110099100100160000100000010110116114003601600001004004940049400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e1f373f4e51inst 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)9fa8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244003930000017550251600281016001810160000501280000110400204003940039199963200281600102016000020480000400394007111160021109101016000010001100223114216211141440036207160000104004040049400404004040049
16002440049300001320460251600101016000010160000501280000115400204003940039199963200191600102016000020480000400394003911160021109101016000010000100228511016211121440037206160000104004040040400404004040040
160024400393000000460251600101016000010160000501280000115400204003940039199963200191600102016000020480000400394003911160021109101016000010000100228511316211141440036206160000104004940040400404004040049
160024400482990000460251600101016000010160000501280000115400294004840048199963200191600102016000020480000400394003911160021109101016000010000100228511116211131940036206160000104004040040400404004040040
160024400393000000460251600101016000010160000501280000115400294003940039199963200191600102016000020480000400714003911160021109101016000010000100228211416211111340036206160000104004040040400404004040040
1600244003930001500460251600101016000010160000501280000115400204003940048199963200191600102016000020480000400394003911160021109101016000010000100228511716211191440036207160000104004040040400404004940040
160024400493001000460251600711016000010160000501280000115400204003940039199963200191600102016000020480000400394003911160021109101016000010000100228511216211181240036206160000104004040040400404004040040
160024400393000000460251600101016000010160000501280000115400214003940039199963200191600102016000020480000400394003911160021109101016000010000100228511316211131940036206160000104004040040400404004040040
160024400393000000460251600101016000010160000501280000115400304003940039199963200281600102016000020480000400484003911160021109101016000010000100228511416211131940068206160000104004040040400404004040040
160024400392990000460251600101016000010160000501280000115400294003940039199963200191600102016000020480000400394003911160021109101016000010000100228511316211171340045206160000104004040040400404004040040