Apple M1 Microarchitecture Research by Dougall Johnson

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

FCADD (vector, 8H)

Test 1: uops

Code:

  fcadd v0.8h, v0.8h, v1.8h, #90
  movi v0.16b, 1
  movi v1.16b, 2

(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)696d6edispatch 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
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372212612548251000100010003983133018303730372415328951000100020003037303711100110004073216222630100030383038303830383038
10043037230612548251000100010003983133022303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100003994216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  fcadd v0.8h, v0.8h, v1.8h, #90
  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)03081e3f4e51inst 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
1020430037225006129548251010010010000100100005004277313130018300373003728268328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225008229548251010010010000126100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250072629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100107101161129634100001003003830038300383003830038
10204300372250063129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225008429548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225072329548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000109640216222963010000103003830038300383003830038
10024300372250146629548251001010100001010149504277313300543003730037282873287671001022101612020000300373003721100211091010100001000003640216222963010000103003830038300383003830038
1002430132225072629548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225053629548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000100640216222963010000103003830038300383003830038
100243003722508429548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000003640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000010640216222963010000103003830038300383003830038
10024300372251626129539251001910100001010000504277313300183003730037282873287671016120100002220000300373003721100211091010100001002000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000003640216222963010000103003830038300383003830038
1002430037225126129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fcadd v0.8h, v1.8h, v0.8h, #90
  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)0318191e1f3f4e51inst 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)9fa0a6a8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001001610010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500006312954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000078211611296340100001003003830038300383003830038
1020430037225000072629548251010010010000100100005004277313130018300853003728265328745101002001000020020000300373003711102011009910010010000100000000710116112963425100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030179300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000011010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030a1e1f3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640516222963010000103003830038300863008630038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010020640216222963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250360612954825100101010000101000050427731313001830226300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222966810000103003830038300383003830038
1002430037224100612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010200640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fcadd v0.8h, v8.8h, v9.8h, #90
  fcadd v1.8h, v8.8h, v9.8h, #90
  fcadd v2.8h, v8.8h, v9.8h, #90
  fcadd v3.8h, v8.8h, v9.8h, #90
  fcadd v4.8h, v8.8h, v9.8h, #90
  fcadd v5.8h, v8.8h, v9.8h, #90
  fcadd v6.8h, v8.8h, v9.8h, #90
  fcadd v7.8h, v8.8h, v9.8h, #90
  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): 0.2505

retire (01)cycle (02)031e1f3f5051inst 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)9fa8a9cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420069150907060258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511021611200360800001002004020040200402004020040
8020420039150004120023258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915000410258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915060410258010010080000100800005006400002002002009020039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420088150270410258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
8020420039150001360258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915090410258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
802042003915090410258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040
80204200391504440410258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010002511011611200360800001002004020040200402004020040
8020420039150300410258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a7a8a9acc2cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)ebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000050200316552003600080000102004020040200402004020040
80024200391500000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000050200416732003600080000102004020040200402004020040
80024200391500000004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010000000050200416452003600080000102004020040200402004020040
80024200391501000004025800101080000108000050640000012002020039200399996310019800102080000201601982006220099218002110910108000010000000050200416442003600080000102004020040200402004020040
8002420039150000000402580010108009912800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000001500050200316342003600080000102004020040200402004020040
80024200391510000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000050200516552003600080000102004020040200402004020040
80024200391500000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000050200516542003600080000102004020040200402004020040
80024200391490000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000050200416332003600080000102004020040200402004020040
80024200391500000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010001000050200316332011700080000102004020040200402004020040
80024200391500000004025800101080000108010750640000002002020039200899996310019800102080000201600002003920039118002110910108000010000000050200516552003600080000102004020040200402004020040