Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLSL2 (by element, 2D)

Test 1: uops

Code:

  smlsl2 v0.2d, v1.4s, v2.s[1]
  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)03181e1f3f4e51inst 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)a1a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230906125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372300010325482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlsl2 v0.2d, v1.4s, v2.s[1]
  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)03080b18191e1f3a3f4e51inst 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)9fa0a1a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300832250000120061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071031622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000003071021622296340100001003003830038300383003830038
10204300372250000000726295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021652296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000004060071021632296340100001003003830038300383023130038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000002071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038
10204301322250000120061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225008229548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100027900640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216232963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316322963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216212963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlsl2 v0.2d, v0.4s, v1.s[1]
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000971011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300180300373003728265328745101002001000020030000300373003711102011009910010010000100014171011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010007571011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010080071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300180300373003728265328745101002001000020030000300373003711102011009910010010000100016571011611296340100001003003830038300383003830038
10204300372250082295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000710116112963421100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100210640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100228640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722400612954844100101010000101000050427867003001830037300372828732878610010201049120300003003730083211002110910101000010084640216222964810000103003830038300383008530085

Test 4: Latency 1->3

Code:

  smlsl2 v0.2d, v1.4s, v0.s[1]
  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)9fa0a1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224912429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250142529548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722508429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722508429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722508429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225084295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000001207101161129634100001003003830038300383003830038
10204300372250265729548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100200007101161129634100001003003830038300383003830038
1020430037225016829548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100002007101161129634100001003003830038300383003830038
102043003722508429548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225016629548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03050818191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000171061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010029436402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722510000061295482510010101000010100005042773133001830037300372828732876710159201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010206402162229630010000103003830038300383003830038
1002430037225000000232295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000012100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlsl2 v0.2d, v8.4s, v9.s[1]
  movi v1.16b, 0
  smlsl2 v1.2d, v8.4s, v9.s[1]
  movi v2.16b, 0
  smlsl2 v2.2d, v8.4s, v9.s[1]
  movi v3.16b, 0
  smlsl2 v3.2d, v8.4s, v9.s[1]
  movi v4.16b, 0
  smlsl2 v4.2d, v8.4s, v9.s[1]
  movi v5.16b, 0
  smlsl2 v5.2d, v8.4s, v9.s[1]
  movi v6.16b, 0
  smlsl2 v6.2d, v8.4s, v9.s[1]
  movi v7.16b, 0
  smlsl2 v7.2d, v8.4s, v9.s[1]
  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)5f6061696d6e74scheduler 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)9fa6a8accfd0d2d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089151051425801001008000010080000500640000015200452006420064032280100200800002002400002006420064111602011009910010016000010001101011150116112006101600001002006520065200652006520065
16020420064150010982580100100800001008000050064000001520045200642006403228010020080000200240000200642006411160201100991001001600001000001011150116112006101600001002006520065200652006520065
160204200641510392580100100800001008000050064000001520045200642006403228010020080000200240000200642006411160201100991001001600001000001011150116112006101600001002006520065200652006520065
160204200641500622580100100800001008000050064000001520045200642006403228010020080000200240000200642006411160201100991001001600001000001011150116112006101600001002006520065200652006520065
1602042006415006225801001008000010080000500640000015200452006420064032280100200800002002400002006420064111602011009910010016000010005031011150116112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000001520045200642006403228010020080000200240000200642006411160201100991001001600001000001011150116112006101600001002006520065200652006520065
1602042006415001442580100100800001008000050064000011520045200642006403228010020080000200240000200642006411160201100991001001600001000101011150116112006101600001002006520065200652006520065
1602042006415008125801001008000010080000500640000015200452006420064032280100200800002002400002006420064111602011009910010016000010005931011151116112006101600001002006520065200652006520065
160204200641500392580100100800001008000050064000011520045200642006403228010020080000200240000200642006411160201100991001001600001000001011150116112006101600001002006520065200652006520065
1602042006415103925801001008000010080000500640000115200452006420064032280100200800002002400002006420064111602011009910010016000010005331011150116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3a3f51inst 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)9fa0a1a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200711500025452580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000010033811102021181920043215160000102004720047200472004720047
16002420046150002545258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000001003384192021119920043215160000102004720047200512004720047
160024200461510024682580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000010060115292042291920047215160000102004720047200472011720047
16002420046150002445258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000001003185292021120920047215160000102004720051200512004720047
160024200461500021932580012128000012800006264000001520031200502005032280012208000020240000200462005011160021109101016000010000010043841192021181920047230160000102004720047200512004720051
16002420046150002187258001212800001280000626400000152002720046200463228001220800002024000020050200501116002110910101600001000001004384176642182020043230160000102004720047200472012920047
16002420128150102145258001212801041280000626408401152003120046200503228001220800002024000020046200461116002110910101600001022153010043841192021120820043215160000102004720047200472004720047
160024200461500027420258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000001004384192042171920047215160000102004720047200472004720047
1600242004615000224252580012128000012800006264000011520027200462004632280012208000020240000200502004611160021109101016000010000010043841202041119820043215160000102004720047200472005120047
1600242005015000254525800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100000100338411920211161920043215160000102005120051200472004720047

Test 6: throughput

Count: 12

Code:

  smlsl2 v0.2d, v12.4s, v13.s[1]
  smlsl2 v1.2d, v12.4s, v13.s[1]
  smlsl2 v2.2d, v12.4s, v13.s[1]
  smlsl2 v3.2d, v12.4s, v13.s[1]
  smlsl2 v4.2d, v12.4s, v13.s[1]
  smlsl2 v5.2d, v12.4s, v13.s[1]
  smlsl2 v6.2d, v12.4s, v13.s[1]
  smlsl2 v7.2d, v12.4s, v13.s[1]
  smlsl2 v8.2d, v12.4s, v13.s[1]
  smlsl2 v9.2d, v12.4s, v13.s[1]
  smlsl2 v10.2d, v12.4s, v13.s[1]
  smlsl2 v11.2d, v12.4s, v13.s[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03080b18191e1f373a3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020430050225000000001040251201001001200001001200005009600001300200300393003914973314997120100200120000200360000300393003911120201100991001001200001000400000007610116113003601200001003004030040300403004030040
1202043003922500000000410251201001001200001001200005009600001300200300393003914973314997120100200120000200360000300393003911120201100991001001200001000000000007610116113003901200001003004030040300403004030040
12020430039225000000350410251202101001200001001200005009600001300200300393003914973314997120100200120000200360000300393003911120201100991001001200001000000000007610116113257801200001003004030040300403004030040
12020430039225000000001040251201001001200001001200005009600001300200300393003914973314997120100200120000200360000300393003911120201100991001001200001000000000007610116113003901200001003004230040300403004030040
1202043003922500000000410251201001001200001001200005009600001300200300393003914973314997120100200120000200360000300393003911120201100991001001200001000000000007610116113174001200001003004030040300403004030040
1202043003922500000000410251201001001200001001200005009600001300200300393003914973314997120100200120000200360000300393092211120201100991001001200001000000000007610116113175701200001003004030040300403004030040
12020430039225000000004102512010010012000010012000050096000013002003003930039158573149971201002001200002003600003003930039111202011009910010012000010000000000076101161231305231200001003065030648309633039630092
120204305782331177927528831151713291571209061271208571231210426341830827131170030708308341564637151591210802021210272023631623035531051911202011009910010012000010022210215132077711711230820181200001003074931159309303042431409
1202043082022701661068616500143601591209281221208231231211326132167334131273030880301441565336155891210522001208542023634683061330251911202011009910010012000010020301418850077522592130121211200001003004030040300403004030040
120204300392250000005204102512010010012000010012000050042861841300203300393003914973314997120100200120000200360000300393003911120201100991001001200001000000000007610116113003601200001003004030040300403004030040

1000 unrolls and 10 iterations

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

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)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)9fa1a8accfd0d2d5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243003923103510302512001010120000101200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010000752000316042309190120000103004030040300403004030040
120024300392250364002512001010120000101201205096000010300203003930039149963159021200102012000020360000300393003911120021109101012000010000752000416022300380120000103004030040300403004030040
12002430039225014002512001010120001101200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010000752000216022317350120000103004130040300403004030040
120024300392380184102512001010120000101200005096000010300203003930039149963167301200102012000020360000300403003911120021109101012000010000752000216024300360120000103004030040300403004030040
120024300392240096402512001010120018101200005099000010300203092230039149963150191200102012000020360000300393003911120021109101012000010203752000316033300360120000103004030040300903004030040
1200243003922501764102512001010120000101200005096000000300203003930039149963150191200102012000020360000300403003911120021109101012000010000752000316022300360120000103004030040300403004030040
12002430039225004002512001010120000101200005096000010300213003930039149963150191200102012000020360000300393003911120021109101012000010000752000216034300360120000103004030040300403004130040
12002430039225004002512001010120000101200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010000752000216022300360120000103004030041300933004030040
1200243003922503540025120010101200001012000050113986300317193003930039149963150191200102012000020360000300393092211120021109101012000010000752000316024300360120000103004030040300403004030040
1200243003922505335202512001010120000101200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010000752000316023300360120000103004030923300413004130040