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, 2D)

Test 1: uops

Code:

  faddp v0.2d, v0.2d, v1.2d
  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)0318191e3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303723000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303723000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303722006612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303723000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303723000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303722000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303722000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303723000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038
1004303723000612548251000100010003983131301830373037241532895100010002000303730371110011000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  faddp v0.2d, v0.2d, v1.2d
  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)030708090a0b1e3a3f4e51inst 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
1020430037225100000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000073521622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3f4e51inst 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
1002430037225000612954825100101010000101000066427731313001830037300372828732876710010201000020200003003730037111002110910101000010000661216222963010000103003830038300383003830038
10024300372250001102954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000712954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  faddp v0.2d, v1.2d, v0.2d
  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)03090b18191e1f3a3f4e51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000090061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500003240061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000371021622296340100001003003830038300383003830038
102043003722500003360061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500003120061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500004475980769295482510100100100001001000053642786700300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500011561040688295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000371021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010172200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500003060061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038
102043003722500003180061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e1f3f4e51inst 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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722401206129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010030640316332966810000103003830038300383003830038
1002430037225024079729548251001010100001010000504277313030018030037301322828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010030640316332963010000103003830038300383003830038
10024300372240906129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018330037300372828732876710010201000020200003003730037111002110910101000010100640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  faddp v0.2d, v8.2d, v9.2d
  faddp v1.2d, v8.2d, v9.2d
  faddp v2.2d, v8.2d, v9.2d
  faddp v3.2d, v8.2d, v9.2d
  faddp v4.2d, v8.2d, v9.2d
  faddp v5.2d, v8.2d, v9.2d
  faddp v6.2d, v8.2d, v9.2d
  faddp v7.2d, v8.2d, v9.2d
  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)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)9fa0a8acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581501684125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000054000511021611200360800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
80204200391506416680201100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
802042003915036412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040
802042003915015412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802021009910010080000100030000511011611200360800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e3a3f51inst 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)9faccfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150110247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050241816016142003680000102004020040200402004020040
8002420039150110247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050241616016142003680000102004020040200402004020040
8002420039161110247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050241316016142003680000102004020040200402004020040
8002420039151110247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050241616016182003680000102004020040200402004020040
80024200391501142247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010350241916017152003680000102004020040200402004020040
8002420039150111824725800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001005024181601482003680000102004020040200402004020040
8002420039150110247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050241516019142003680000102004020040200402004020040
800242003915011024725800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001005024161601692003680000102004020040200402004020040
8002420039150116247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010350241616216182003680000102004020040200402004020040
8002420039150110247258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010050241616013152003680000102004020040200402004020040