Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDHN2 (vector, 2D)

Test 1: uops

Code:

  addhn2 v0.4s, v1.2d, v2.2d
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03181e3f4e51inst 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
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100030003037303711100110000373116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  addhn2 v0.4s, v1.2d, v2.2d
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3a3f4e51inst 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)9fa8a9acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071002162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071002162229634100001003022830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003721102011009910010010000100000071002162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071002162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100400073602162229634100001003003830038300383003830038
102043003722510008229548251010010010000100100005004277313130018300373003728265328745102512001000020030000300373003711102011009910010010000100100071002162229634100001003003830038300383003830038
1020430037225000010329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100103071002162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100100071002162329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071002163229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071002162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640416222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001010640216232963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001010640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216232963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216232963010000103003830038300383003830038
1002430037225022429548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216232963010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316222963010000103003830038300383003830038
100243003722506129548251001810100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250101129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216322963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  addhn2 v0.4s, v0.2d, v1.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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
10204300372250015032954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225009822954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000285371011611296340100001003003830038300383003830038
1020430037225009742954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250011322954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250012342954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225009772954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225009722954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250010022954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250010392954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3a3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500015182954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500018972954825100101010000101000050427731313001830037300372828732876710010221000020300003003730037111002110910101000010000660216332963010000103003830086300383003830038
1002430037225308814832954825100101010000101000050427731303001830037300372828732876710010201000020309783008430037111002110910101000010100640216222963010000103003830038300383003830038
10024300372250120110332954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500019002954825100101010000101000050427731313012630037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500012542954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372240001612954825100101010000101000050427731303001830037300842828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500011032954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372240001842954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000116629548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100870640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  addhn2 v0.4s, v1.2d, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa0a6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400033229548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500014929548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500019129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722400094829548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000207101160129634100001003003830038300383003830038
1020430037225000267429548251010010010000100100005004278670300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500014729548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129691100001003003830038300383003830038
102043003722500014929548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500017029548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830083
102043003722500032129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500010329548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295484410010101000010101495042786703001803003730225282871028786100102010000203000030037300371110021109101010000102253256110640216222963010000103003830038300383003830038
100243018022521210329548102100201010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000030640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010001002640216222963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731330018030037300842828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010001000640216222963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010001000668216222963010000103003830038300383003830226
100243003722500612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010001000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100035000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100055000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  addhn2 v0.4s, v8.2d, v9.2d
  movi v1.16b, 0
  addhn2 v1.4s, v8.2d, v9.2d
  movi v2.16b, 0
  addhn2 v2.4s, v8.2d, v9.2d
  movi v3.16b, 0
  addhn2 v3.4s, v8.2d, v9.2d
  movi v4.16b, 0
  addhn2 v4.4s, v8.2d, v9.2d
  movi v5.16b, 0
  addhn2 v5.4s, v8.2d, v9.2d
  movi v6.16b, 0
  addhn2 v6.4s, v8.2d, v9.2d
  movi v7.16b, 0
  addhn2 v7.4s, v8.2d, v9.2d
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0308090a3f51inst 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)60696b6d6escheduler 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420091150000284425801001008000010080000500640000120045020064200643228010020080000200240312202282006411160201100991001001600001000049301011221611200611600001002006520065200652006520065
1602042015515000039258010010080000100800005006400000200450200642006432280100200800002002400002006420064111602011009910010016000010000001011611611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000200450200642006432280100200800002002400002006420064111602011009910010016000010000001011211611200611600001002006520065200652006520065
16020420064150000186258010010080000100800005006400001200450200642006432280100200800002002400002006420064111602011009910010016000010000001011111611200611600001002006520065200652006520065
1602042006415000039258010011580000100800005006400001200450200642006436380531200803132002400002006420064111602011009910010016000010000001011111611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000200450200642006432280100200800002002400002006420064111602011009910010016000010000301011211611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000200450200642006432280100200800002002400002006420064111602011009910010016000010000001011211611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000200450200642006432280100200800002002400002006420064111602011009910010016000010000001011211611200611600001002006520065200652006520065
1602042006415000062258010010080000100800005006400001200450200642006432280100200800002002400002006420064111602011009910010016000010000001011111611200611600001002006520065200652006520065
1602042006415100039258010010080000100800005006400000200450200642006432280100200800002002400002006420064111602011009910010016000010010001011211611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa1a8a9c2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007115000512580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100293118202113420043215160000102004720047200472004720047
1600242004615000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100273113202114320043215160000102004720047200472004720047
1600242004615000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100273117202113420043215160000102004720047200472004720047
1600242004615000452580012128000012800006264000011200312004620046322800122080000202400002004620046111600211091010160000100000100273113202113420043215160000102004720051200472004720047
16002420046150001522580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100276119202114320043215160000102004720047200472004720047
1600242004615000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100293115202214320043215160000102004720047200472004720047
1600242004615000452580012128009612800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100263118202116620043215160000102004720047200472004720047
1600242004615000512580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100273118202114420043215160000102004720047200472004720047
16002420046150001922580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100303117202113420043215160000102004720047200472004720047
1600242004615700452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100313118202116420043215160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  addhn2 v0.4s, v16.2d, v17.2d
  addhn2 v1.4s, v16.2d, v17.2d
  addhn2 v2.4s, v16.2d, v17.2d
  addhn2 v3.4s, v16.2d, v17.2d
  addhn2 v4.4s, v16.2d, v17.2d
  addhn2 v5.4s, v16.2d, v17.2d
  addhn2 v6.4s, v16.2d, v17.2d
  addhn2 v7.4s, v16.2d, v17.2d
  addhn2 v8.4s, v16.2d, v17.2d
  addhn2 v9.4s, v16.2d, v17.2d
  addhn2 v10.4s, v16.2d, v17.2d
  addhn2 v11.4s, v16.2d, v17.2d
  addhn2 v12.4s, v16.2d, v17.2d
  addhn2 v13.4s, v16.2d, v17.2d
  addhn2 v14.4s, v16.2d, v17.2d
  addhn2 v15.4s, v16.2d, v17.2d
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03080b18191e373f4e51inst 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)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)9fa0a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440075300000000410251601011001600011001600005002398999014002040048400391997331999716010020016000020048000040040400491116020110099100100160000100000001011021611400361600001004004940050400404004040040
16020440048299000300420251601001001600171001600005001280000014002140039400711997331999816010020016014220048000040048400391116020110099100100160000100000201014411611400461600001004004040491402254019440050
160204400483001133015070651605961101602551101600005001280000014002040048400401997332000616010020016000020048000040039400401116020110099100100160000100010001011011611400361600001004004040041400414004040040
16020440039300000000410251601001001600011001600005001280000014002140039400481997331999716010020016000020048000040039400391116020110099100100160000100060001011011611400361600001004004140050400404004940040
160204400483000000017410251601011001600171001600005001280000014002940040400391997332000616010020016000020048000040039400401116020110099100100160000100000001011011611400361600001004004140040400414004940049
16020440039300000000420251601171001600171001600005001319999014002040039400711997331999816010020016000020048000040039400711116020110099100100160000100000001011011611400371600001004004040040400414005040041
16020440039300000000500251601171001600171001600005001280000014002140040400391997331999716010020016000020048000040040400401116020110099100100160000100000001011011611400451600001004004040040400404004040050
16020440039299000001420251601171001600001001600005001280000014003040049400481997332000616010020016000020048000040048400401116020110099100100160000100000001011011611400501600001004004040040400404004140050
16020440040300000000930251601011001600001001600005002398999014002040039400391997332000716010020016000020048000040071400391116020110099100100160000100000001011011611400361600001004004040072400404004040049
160204400393000000017500251601001001600001001600005001319998014002140040400401997331999816010020016000020048000040048400391116020110099100100160000100000001011011611400361600001004004040050400494004940041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e373a3f51inst 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)5f6061696b6d6edispatch 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)9fa0a6accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004830000012722251600271016001710160000501280000115400210400394004819989032001216001020160000204800004003940040111600211091010160000100000100268212116211181140045209160000104004040049400404004140040
1600244003930000002482516002710160000101600005012800001154002104003940048199890320021160010201600002048000040049400391116002110910101600001000001002611311716211191740036409160000104004140049400404004940040
160024400393000000256251600101016000010160000501319999110400200400394004819989032002116001020160000204800004003940149111600211091010160000102030100268211916211191840045209160000104004040049400404004940049
160024400483000000248251600101016000010160000502398999110400290400394003919989732001216001020160000204800004003940048111600211091010160000100000100268211916211162040036208160000104004040040400404004940049
1600244004830000017247251600101016000010160000501280000115400200400404003919989032002116001020160000204800004003940040111600211091010160000100000100268211816421171340036207160000104004040049400404004140040
16002440039299000172712251600101016001710160000502398999115400210400484003919989032001316001020160000204800004004840039111600211091010160000100000100268111816211191840045209160000104004140040400504004040040
1600244004830000017256251600271016001710160000502398999115400290400484003919989032001216001020160000204800004003940040111600211091010160000100000100268112116411161740045209160000104004040040400404004940049
1600244003930000017247251600101016001710160000502398999115400200400404004819989032001216001020160000204800004003940048111600211091010160000107000100268211816211181940036209160000104004040049400404004040049
160024400393000001256251600101016000110160000502398999115400210400484003919989032001216001020160000204800004003940039111600211091010160000100000100263211916211191840045209160000104004940049400494004040050
160024400393000000256251600271016001710160000501280000115400200400394004019989032002216001020160000204800004004940039111600211091010160000100000100268211916211182040036207160000104004040049400404004940049