Apple M1 Microarchitecture Research by Dougall Johnson

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

UABAL2 (vector, 8H)

Test 1: uops

Code:

  uabal2 v0.8h, v1.16b, v2.16b
  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
1004303723084254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100002790073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100056073116112630100030383038303830383038
10043037230105254825100010001000398313130183037303724153289510001000300030373037111001100010073116112630100030383038303830383038
10043037230105254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  uabal2 v0.8h, v1.16b, v2.16b
  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)03191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225030061295482510110100100001001000050042773131300183003730037282883287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300223003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013162229634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

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)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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100011037640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010020640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500662954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  uabal2 v0.8h, v0.16b, v1.16b
  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)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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225024612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225015612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003721102021009910010010000100001507101161129634100001003003830038300383003830038
10204300372240025129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100004807101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225007102954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000027101161129634100001003003830038300383003830038

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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037224000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037224000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000306402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000108612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000026402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010102985042773130300183008430275283143228900110112210983203341730369303687110021109101010000100430121895307863412429865310000103041430368303683003830368

Test 4: Latency 1->3

Code:

  uabal2 v0.8h, v1.16b, v0.16b
  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)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
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007102161129634100001003003830038300383003830038
102043003722500224295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000307101161129634100001003003830038300383003830038
102043003722400726295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000017101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000000612954825100101010000101000050427752630018030037300372828732876710010201000020300003003730037111002110910101000010000010006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000892954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000002006402162229630010000103003830038300383003830038
100243003722500000004508294941411002012100481210894554286776301620303683032128327628892109082411143243148230367303677110021109101010000100020021776327664654229882310000103037030357303583036630323

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  uabal2 v0.8h, v8.16b, v9.16b
  movi v1.16b, 0
  uabal2 v1.8h, v8.16b, v9.16b
  movi v2.16b, 0
  uabal2 v2.8h, v8.16b, v9.16b
  movi v3.16b, 0
  uabal2 v3.8h, v8.16b, v9.16b
  movi v4.16b, 0
  uabal2 v4.8h, v8.16b, v9.16b
  movi v5.16b, 0
  uabal2 v5.8h, v8.16b, v9.16b
  movi v6.16b, 0
  uabal2 v6.8h, v8.16b, v9.16b
  movi v7.16b, 0
  uabal2 v7.8h, v8.16b, v9.16b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042008915003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000001011231622200611600001002006520065200652006520065
160204200641502523925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
160204200641502673925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
16020420064150021025801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100048001011221622200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000001011221622200611600001002006520065200652006520065
1602042006415103925801001008000010080000500640000020045200642006432280100200800002002400002013320064111602011009910010016000010000001011221622200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f3a3f51inst 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)9fa0a1a7a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007015000000000004586800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100000000100318113020211141320043215160000102004720047200472004720047
16002420046150000000000045888001212800001280000626400001152002720101200463228001220800002024000020046200461116002110910101600001002060528010037841142021114720043215160000102013520128201352016720047
16002420046150010000013800458680012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000100010035841920211161220043215160000102004720047200472004720047
160024200461500000000000457680012128000012800006264000001520031200502005032280012208000020240000200502005011160021109101016000010000000010040115272442214720047230160000102005120051200512005120047
16002420046150000000000045558001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000000001002984111202116620043215160000102004720047200472004720047
1600242005015000000000004555800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100003001560100318415202117720043215160000102004720047200472004720047
1600242004615000000000007267800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100000000100308527242226820047230160000102004720047200472004720051
1600242004615000000000005157800121280000128000062640000015200312005020050322800122080000202400002005020050111600211091010160000100003303010034115282042213720047215160000102005120051200512005120051
16002420050150000000000045578001212800001280000626400000152003120050200503228001220800002024000020050200461116002110910101600001000037010201003111516242214620043215160000102005120051200512005120047
160024200461500000000000235728001212800001280000626400001152003120050200463228001220800002024000020046200501116002110910101600001000031000100371152132442281320047215160000102005120051200512005120051

Test 6: throughput

Count: 16

Code:

  uabal2 v0.8h, v16.16b, v17.16b
  uabal2 v1.8h, v16.16b, v17.16b
  uabal2 v2.8h, v16.16b, v17.16b
  uabal2 v3.8h, v16.16b, v17.16b
  uabal2 v4.8h, v16.16b, v17.16b
  uabal2 v5.8h, v16.16b, v17.16b
  uabal2 v6.8h, v16.16b, v17.16b
  uabal2 v7.8h, v16.16b, v17.16b
  uabal2 v8.8h, v16.16b, v17.16b
  uabal2 v9.8h, v16.16b, v17.16b
  uabal2 v10.8h, v16.16b, v17.16b
  uabal2 v11.8h, v16.16b, v17.16b
  uabal2 v12.8h, v16.16b, v17.16b
  uabal2 v13.8h, v16.16b, v17.16b
  uabal2 v14.8h, v16.16b, v17.16b
  uabal2 v15.8h, v16.16b, v17.16b
  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)031e373f51inst 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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044004930000502516010010016001710016000050012800001400200400394003919973032000916010020016000020048000040039400391116020110099100100160000100025410110116114003641600001004004040040400404004040040
160204400393000041251601001001600001001600005001280000140020040039400481997303199971601002001600002004800004003940048111602011009910010016000010000010110116114003601600001004004040040400404004040040
16020440039300017715251601001001600001001600005001280000140021040039400391997303199971601002001600002004800004003940039111602011009910010016000010000010110116114003601600001004004040040400404004040040
160204400393000041251601001001600001001600005002398999140020040039400391997303199971601002001600002004800004003940048111602011009910010016000010000010110116114004501600001004004940040400494004040040
160204400392990041251601001001600171001600005002398999140020040039400391997373199971601002001600002004800004003940039111602011009910010016000010000010110116114004501600001004005040040400414004940040
1602044003930000412516010010016000010016000050012800001400200400394004819973032000616010020016000020048000040039400391116020110099100100160000100210010110116114008701600001004005040040400404004040040
160204400393000041251601171001600001001600005001280000040020040039400491997303199981601002001600002004800004003940039111602011009910010016000010000010110116114003601600001004004040040400494004040049
1602044003930001750251601001001600001001600005002398999140020040039400391997303199981601002001600002004800004004840039111602011009910010016000010000010110116114004601600001004004040040400404004940040
160204400393000042251601171001600001001600005001280000040020040039400391997303199971601002001600002004800004003940039111602011009910010016000010003010110116114003601600001004025740040400534010440049
160204400393000041251601001001600001001600005001280000140020040039400391997303199971601002001600002004804084003940039111602011009910010016000010000010110116114003601600001004004040040400534004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f373f51inst 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)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)9fa1a6a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)dfe0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440048300000150046251600101016001710160000502398999110400200400484003919996320019160010201600002048000040048400391116002110910101600001000100010026114115162111610340036206160000104004040049400504004040040
16002440039300000001755251600101016000010160000501280000115400200400394003919996320019160010201600002048000040048400391116002110910101600001000403901002685113162111912340036206160000104004040040400494031840040
1600244003930000000046251601261016000010160000501280000015400200400394003919996320019160010201600002048000040048400391116002110910101600001000106010026115116162111717340045206160000104004040049400474004140040
16002440048299000901746251600101016000010160000502398999015400290400394003919996320028160010201600002048000040039400481116002110910101600001000300010026115122162111117340045206160000104004040040400544004140040
160024400393000000001591251600101016000010160000501280000115400200400394003919996320019160010201600002048000040039400391116002110910101600001000200010026115111162111611340045206160000104004040049400494004140040
1600244004830000000046251600101016000010160000501280000115400200400394003919996320019160010201600002048000040048400391116002110910101600001000300010026115113162111611340036206160000104004040040400454004040040
1600244003930000000046251600101016000010160000501280000115400200400394004819996320019160010201600002048000040048400391116002110910101600001000003010026115116162111116340036206160000104004940101400454004140050
1600244003930000000046251600271016000010160000502398999115400200400394003919996320019160010201600002048000040039400481116002110910101600001000200010026115120162111616340045209160000104004040049400494004940040
1600244003930000000055251600101016000010160000501280000115400200400394005219996320019160010201600002048000040039400391116002110910101600001000300010026115116162111116340045206160000104004040040400494004040040
160024400483000000001015251600101016001710160000501280000115400200400394003919996320019160010201600002048000040048400391116002110910101600001000300010026115120162111818340036209160000104004040040400494004040040