Apple M1 Microarchitecture Research by Dougall Johnson

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

FADDP (vector, 2S)

Test 1: uops

Code:

  faddp v0.2s, v0.2s, v1.2s
  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)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)a6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116113034100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037231656125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  faddp v0.2s, v0.2s, v1.2s
  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)03080b1e3f4e51inst 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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000662954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000103295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000240007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037224000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037224000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250007262954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010020007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a0b18191e3a3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225110000268295482510010101000810100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000644516111129630010000103003830038300383003830038
10024300372251100002682954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100006441016111029630010000103003830038300383003830038
10024300372251100002682954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100006441016101029630010000103003830038300383003830038
100243003722511000026829548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001003064461610829630010000103003830038300383003830038
1002430037225110000268295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000644101610529630010000103003830038300383003830038
1002430037225110000268295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000644516101029630010000103003830038300383003830038
10024300372251100002682954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100006441016101029630010000103003830038300383003830038
10024300372251100002682954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100006441016101029630010000103003830038300383003830038
10024300372251100002682954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100606441016101029630010000103003830038300383003830038
10024300372251100002682954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100006441016101029630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  faddp v0.2s, v1.2s, v0.2s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037224029329548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830083
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225018029548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722406129548441010010010000100100005004277313130018300373003728265328745101002001000020020000300373008411102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300831110021109101010000100870640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100750640216222963010000103003830038300383003830038
1002430037225008929548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100900640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050428274103001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100840640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130066300373003728287328767100102010000202000030037300371110021109101010000100810640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222979410000103003830038300383003830038
100243003722527061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001001050640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050428138403001830037300372828732876710160201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100810640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  faddp v0.2s, v8.2s, v9.2s
  faddp v1.2s, v8.2s, v9.2s
  faddp v2.2s, v8.2s, v9.2s
  faddp v3.2s, v8.2s, v9.2s
  faddp v4.2s, v8.2s, v9.2s
  faddp v5.2s, v8.2s, v9.2s
  faddp v6.2s, v8.2s, v9.2s
  faddp v7.2s, v8.2s, v9.2s
  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)0318191e1f3a3f51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000002462580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000100511481699200360800001002004020040200402004020040
8020420039150000024625801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000005114101699200360800001002004020040200402004020040
8020420039150000024625801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000005114916109200360800001002004020040200402004020040
802042003915000002462580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511491699200360800001002004020040200402004020093
8020420039150000024625801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000005114101674200360800001002004020040200402004020040
8020420039150000024625801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000007005114916104200360800001002004020040200402004020040
8020420039150000021032580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000100511410161010200360800001002004020040200402004020040
80204200391500000246258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051141016410200360800001002004020040200402004020040
802042003915000002462580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000100511441699200360800001002004020040200402004020040
802042003915000002462580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511491699200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a1e3f51inst 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
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000101005020141617172003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502017166172003680000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000102230502014161782003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001010050208161782003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010100502017166172003680000102004020040200402004020199
800242003915000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502014166172003680000102004020040200402004020040
800242003915000135258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050207161772003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000101005020161617172003680000102004020040200902004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001044930502014161462003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000104030502017166172003680000102004020040200402004020040