Apple M1 Microarchitecture Research by Dougall Johnson

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

FABD (scalar, S)

Test 1: uops

Code:

  fabd s0, s0, s1
  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)03181e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230012625482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037220216125482510001000100039831303018303730372415328951000100020003037303711100110000373216222630100030383038303830383038
10043037220013625482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303722008225482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037220028225482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  fabd s0, s0, s1
  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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011612296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100200071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373008011102011009910010010000100000071021611296340100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000001137295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000001631295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006404162229630010000103003830038300383003830038
100243003722500060061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000441061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000084295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000001352295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000084295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000084295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773133001830037300372828732876710010201017920200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000001072954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000110006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fabd s0, s1, s0
  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)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)9fa0a6a8a9acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250145295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250187295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250544295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000017101161129634100001003003830038300383003830038
10204300372250521295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250473295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250446295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250128295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129708100001003003830038300383003830038
10204300372250431295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250495295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250529295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038

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
10024300852251261295482510010111000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316222963010000103003830038300383003830038
1002430037225961295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250768295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240346295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250726295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240251295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250536295482510018101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fabd s0, s8, s9
  fabd s1, s8, s9
  fabd s2, s8, s9
  fabd s3, s8, s9
  fabd s4, s8, s9
  fabd s5, s8, s9
  fabd s6, s8, s9
  fabd s7, s8, s9
  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)030a0b181e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048150000124125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051102161120036800001002004020040200402004020040
8020420039150000124125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
8020420039150000041258010010080000100800005006400002002002003920039997329999780100200800002001600002003920039118020110099100100800001000051101161420036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000200830201062003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000094125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802052003915000004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000034125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000200200200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

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)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)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481501213525800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050207166220036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050203162420036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050204164220036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050206163420036080000102004020040200402004020040
80024200391502974025800101080000108000050640000120020200622003999963100198001020800002016000020039200391180021109101080000100050202164220036080000102004020040200402004020040
8002420039150214025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050202162420036080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050204163420036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050204162420036080000102004020040200402004020040
80024200391503664025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050204164220036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050204164220036080000102004020040200402004020040