Apple M1 Microarchitecture Research by Dougall Johnson

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

UABAL (vector, 4S)

Test 1: uops

Code:

  uabal v0.4s, v1.4h, v2.4h
  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)030b1e1f3f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
1004303722000197254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
100430372310061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
1004303722000255254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000300030373037111001100073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  uabal v0.4s, v1.4h, v2.4h
  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)0307080a0b18191e1f3a3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722510100000165295482510100100100001001000050042773133001830037300372826532874510100208100002003000030037300371110201100991001001000010000007134165529634100001003003830038300383003830038
1020430037225101000001128295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007134163429634100001003003830038300383003830038
102043003722510100000265295482510100100100001001000050042773133001830037300372826532874510708200100002003000030037300371110201100991001001000010000007134165529634100001003003830038300383003830038
1020430037225101000001166295482510112104100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007135165529634100001003003830038300383003830038
102043003722510100000165295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007125163529634100001003003830038300383003830038
102043003722510100000165295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007435165629634100001003003830038300383003830038
102043003722510100000165295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007135164529634100001003003830038300383003830038
1020430037225101000120165295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007135164529634100001003003830038300383003830038
102043003722510100000165295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007134164429634100001003003830038300383003830038
102043003722510100000165295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007133164529634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001236402162329630010000103003830038300383003830038
10024300372250006794295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162329630010000103003830038300383003830038
10024300372250006902954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000846402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001022101682030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042786700300183003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000066402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  uabal v0.4s, v0.4h, v1.4h
  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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722503906129548251010010010000100100005004277313130018300373003728265328745102532001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225100000030612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006404164329630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731303001830037300372828772878610010201000020300003003730037111002110910101000010000000006404164329630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006403164329630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000100006404164329630010000103003830038300383003830038
10024300372250000110147104612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000003006404163429630010000103003830038300383003830038
1002430037224000000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006404164429630010000103003830038300383003830038
1002430037225000000000822954825100101010000101000050427731303012630037300372828732878610010201000020300003003730037111002110910101000010000000006404164329630010000103003830038300383003830038
1002430037225000000000822954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006403163429630010000103003830038300383003830038
1002430037225000000000612954825100101010008101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006403164429630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006404164329630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  uabal v0.4s, v1.4h, v0.4h
  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)03080b181e1f3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954846101231001000010010000500427731330018030037300372826532875810100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000001562954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000002512954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037224000360612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000810010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773130300183003730037282873287671015920100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183008430037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000670216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  uabal v0.4s, v8.4h, v9.4h
  movi v1.16b, 0
  uabal v1.4s, v8.4h, v9.4h
  movi v2.16b, 0
  uabal v2.4s, v8.4h, v9.4h
  movi v3.16b, 0
  uabal v3.4s, v8.4h, v9.4h
  movi v4.16b, 0
  uabal v4.4s, v8.4h, v9.4h
  movi v5.16b, 0
  uabal v5.4s, v8.4h, v9.4h
  movi v6.16b, 0
  uabal v6.4s, v8.4h, v9.4h
  movi v7.16b, 0
  uabal v7.4s, v8.4h, v9.4h
  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)03080b1e3f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420088150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001001001011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001001001011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641500003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010011001011111611200611600001002006520065200652006520310
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001002001011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000001011111611200611600001002006520065200652006520065
160204200641500003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010041901011111611200611600001002006520065200652006520065
16020420064150000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001005112901011111611200611600001002006520065200652006520065
160204200641500003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010038601011111611200611600001002006520065200652006520065

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)9fa1a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420072150000452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000100318111025211819200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000100578311925211209200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000010520032200512005132280012208000020240000200512005111160021109101016000010000100318412025211719200482201160000102005220052200612005220052
1600242005115000045278001212800001280000626400001102003220060200513228001220800002024000020051200511116002110910101600001000010035341925211199200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000011020032200512006032280012208000020240000200512005111160022109101016000010000100433421925212197200482201160000102005220052200612005220052
16002420051150000452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000100438119252211619200482401160000102005220052200522005220052
16002420051150000452780012128000012800006264000010520032200512005132280012208000020240000200512005111160021109101016000010000100338411934211197200482201160000102005220052200612005220052
16002420051150000452980012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000100358111625221197200482201160000102005220052200612005220061
1600242005115000045278001212800001280000626400001152004120051200603228001220800002024000020051200511116002110910101600001000010034852834412919200572402160000102005220052200612005220061
160024200511500004527800121280000128000062640000110200322005120051322800122080000202400002005120060111600211091010160000100001004381712025211916200482201160000102005220052200612005220052

Test 6: throughput

Count: 16

Code:

  uabal v0.4s, v16.4h, v17.4h
  uabal v1.4s, v16.4h, v17.4h
  uabal v2.4s, v16.4h, v17.4h
  uabal v3.4s, v16.4h, v17.4h
  uabal v4.4s, v16.4h, v17.4h
  uabal v5.4s, v16.4h, v17.4h
  uabal v6.4s, v16.4h, v17.4h
  uabal v7.4s, v16.4h, v17.4h
  uabal v8.4s, v16.4h, v17.4h
  uabal v9.4s, v16.4h, v17.4h
  uabal v10.4s, v16.4h, v17.4h
  uabal v11.4s, v16.4h, v17.4h
  uabal v12.4s, v16.4h, v17.4h
  uabal v13.4s, v16.4h, v17.4h
  uabal v14.4s, v16.4h, v17.4h
  uabal v15.4s, v16.4h, v17.4h
  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)03071e373f4e51inst 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)9fa0a1a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044004830000174102516011710016006110016000050012800001400304003940049199733199971601002001600002004800004004940039111602011009910010016000010000200010110116114003601600001004024340049400404004140050
1602044003930000174202516011710016000010016000050012800001400204003940049199733199971601002001600002004800004004940039111602011009910010016000010000000010110116114004601600001004004040041400504004040040
1602044003930000175002516010010016001710016000050012800001400294004840039199733199971601002001600002004800004004840039111602011009910010016000010000000010110116114003601600001004004940040400504004040040
160204400393000004102516016110016001710016000050012800001400294003940039199733199971601002001600002004800004004940039111602011009910010016000010000000010110116114003601600001004004040040400404004040040
1602044004930000041025160117100160000100160000500239902714002040049400391997310200091601002001600002004800004003940049111602011009910010016000010000000010110116114003601600001004004040050400404004940040
1602044003930000070602516010010016000010016000050012800001400294004840039199733199971601002001600002004800004003940039111602011009910010016000010000000010110116114003601600001004024540049400494005040040
160204400402990004102516011710016006110016000050027983641400304003940049199733199971601002001600002004800004003940049111602011009910010016000010000000010110116114004601600001004004940040400414004040040
16020440039300001741252516010010016001710016000050012800001400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000010110116114003601600001004004140041400404004040041
160204400393000005002516016110016006110016000050023989991400204003940048199733200071601002001600002004800004004940039111602011009910010016000010000000010110116114003601600001004007240049400404005040040
160204400493000004102516010110016000010016000050023990271400204004040039199733200071601002001600002004800004004040049111602011009910010016000010000000010110116114003601600001004004040050400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318373f51inst 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)9fa6accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004830000552516002710160017101601525023989991154002040048400391999632001916001020160000204800004004840039111600211091010160000100010022821121621111740036155160000104004940040400494004940049
1600244004830001746251600101016000010160000501280000115400294004840039199963200281600102016000020480000400484003911160021109101016000010001002282110162119940045155160000104004040049400404004940049
16002440048300005525160027101600171016000050239899911540029400484003919996320019160010201600002048000040048400391116002110910101600001000100228217162118940036155160000104004940040400494004040049
16002440048300017472516002710160017101600005023989991154002940048401301999632001916001020160000204800004004840048111600211091010160000100010022821916211101240036155160000104004940040400494004040040
160024400393000175525160010101600001016000050239899911540029400394004819996320019160010201600002048000040039400481116002110910101600001000100228211216211111040045155160000104004940040400404004040049
16002440039300017552516002710160017101600005012800001154002940048400481999632002816001020160000204800004004840039111600211091010160000100010022821816211111040036155160000104004940040400494004940040
16002440040300004625160027101600171016000050128000011540029400484004819996320019160010201600002048000040039400481116002110910101600001000100228219162119940045155160000104004940040400494010040049
16002440039300017552516001010160017101600005012800001154002940039400481999632001916001020160000204800004004840039111600211091010160000100010022822916211101140045155160000104004940040400494004040049
16002440048300017552516001010160017101600005023989991154002940039400481999632002816001020160000204800004003940039111600211091010160000100010022821916211111040045155160000104004040049400404004940049
16002440048300006925160010101600001016000062239899911540029400484014719996320156160010201601072048000040048400481116002110910101600001023100228218162119740045355160000104004940040400494004940049