Apple M1 Microarchitecture Research by Dougall Johnson

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

UQADD (vector, 8B)

Test 1: uops

Code:

  uqadd v0.8b, v0.8b, v1.8b
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043084230006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830843038
100430372300017025482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220008425482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372200917025482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230066125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd v0.8b, v0.8b, v1.8b
  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)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)60696d6edispatch stall (70)72scheduler 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295482510100100100001001000050042773131300183008530037282650328745101002001016420020000300373003711102011009910010010000100200028307101161129634100001003003830038300383003830038
102043003722500000103295482510100100100001001000063842773130300183003730037282650328764101002001000020020000300373003711102011009910010010000100000007121161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100000007100161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500012061295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100003237331252129670100001003003830038300383003830038
102043003722510008861295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500000103295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000000006403162229630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000009306402162229630010000103003830038300383003830038
10024300372250000000000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000000612954825100101010000101000050427731313001803003730037282873287671001022100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372240000000000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000000612954825100101010000101000050427731313001803003730037282873287671001020100002020326300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500000003900612954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000000612954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd v0.8b, v1.8b, v0.8b
  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)0308090b181e1f3f4e51inst 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
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110202100991001001000010000000071011611296340100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000003071011611296540100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002036430037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307181e3f4e51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640316222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722800061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001040640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001010640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222970210000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003723200361295484410010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001803003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250017161295482510010101000010100005042773133001803003730037282873287671001020100002020000300843003711100211091010100001000642216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd v0.8b, v8.8b, v9.8b
  uqadd v1.8b, v8.8b, v9.8b
  uqadd v2.8b, v8.8b, v9.8b
  uqadd v3.8b, v8.8b, v9.8b
  uqadd v4.8b, v8.8b, v9.8b
  uqadd v5.8b, v8.8b, v9.8b
  uqadd v6.8b, v8.8b, v9.8b
  uqadd v7.8b, v8.8b, v9.8b
  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)030b181e3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391500089741258010010080000100800005006400001200202003920347997339997801002008010420016021420094200951180201100991001008000010000153511031612200360800001002004020040200402004020040
802042003915000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000162511011611200360800001002004020040200402004020040
8020420039150010412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000832580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200392180201100991001008000010000159511011612200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003914900183412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000050201161120036080000102004020040200402004020040
800242003915000000100040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000003050201161120036080000102004020040200402004020040
800242003915000000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000306050201161120036080000102004020040200402004020040
8002420039150000000120040258001010800001080000506416040200202003920039999681001980010208000020160000201902003951800211091010800001000209050201161120036080000102004020040200402004020040
800242003915000000000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000050201161120036080000102004020040200402004020040
800242003915200000000040258001010800001080000506400001200202019220039999631001980010208000020160000200392003911800211091010800001000000050201161120036080000102004020040200402004020040
800242003915000000000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000050201161120036080000102004020040200402004020040
800242003915000000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000050201161120036080000102004020040200402004020040
800242003915000000000040258001010800801080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000050201161120036080000102004020040200402004020040
80024200391500000004200040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001002000050201161120036080000102004020040200402004020040