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, 4S)

Test 1: uops

Code:

  uqadd v0.4s, v0.4s, v1.4s
  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)a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000033473116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000020073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd v0.4s, v0.4s, v1.4s
  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)03041e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722510126295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830085
102043003722500145295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383008130038
102043003722500124295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500145295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500124295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250082295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500166295482510100100100001001000050042773131300183003730037282653287451010020010000204200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500166295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500145295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640316222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500103295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225001186295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500151295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216212963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd v0.4s, v1.4s, v0.4s
  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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722501542954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372240842954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722501662954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722501452954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722501242954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722501662954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e3f4e51inst 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
100243003722400061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006612162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000571295482510010101000010101495042773130300543003730037282873287671030920101682020000300373022711100211091010100001002006402162229630010000103003830038300383003830038
100243003722500061295482510021111000811100005042773130300183003730037282913287671001020101672020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225001561295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722510061295482510010101000012100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000306402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000306612162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd v0.4s, v8.4s, v9.4s
  uqadd v1.4s, v8.4s, v9.4s
  uqadd v2.4s, v8.4s, v9.4s
  uqadd v3.4s, v8.4s, v9.4s
  uqadd v4.4s, v8.4s, v9.4s
  uqadd v5.4s, v8.4s, v9.4s
  uqadd v6.4s, v8.4s, v9.4s
  uqadd v7.4s, v8.4s, v9.4s
  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)6061696d6edispatch 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)9fa0a6a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004815005262580100100800001008000050064000012200202003920039997339997801002008000020016000020039200391180201100991001008000010002165110002161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110001161120036800001002004020040200402004020040
80204200391500562580100100800001008000050064000010200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110001161120036800001002004020040200402004020040
802042003915007062580100100800001008000050064000002200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110001161120036800001002004020040200402004020040
8020420039150511252580100100800001008000050064000012200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110201161120036800001002004020040200402004020040
80204200391500852580100100800001008000050064000012200202003920039997339997801002008000020016000020039200391180201100991001008000010040005110221161120036800001002004020040200402004020040
802042003915001252580100100800001008000050064000012200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110221161120036800001002004020040200402004020040
802042003915004962580100100800001008000050064000012200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110221161120036800001002004020040200402004020040
802042003915001292580100100800001008000050064000012200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110201161120036800001002004020040200402004020040
802042003915001252580100100800001008000050064000012200202003920039997339997801002008000020016000020039200391180201100991001008000010000005110201161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)6061696d6edispatch 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)9fa1a6a8acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150001052580010108000010800005064000005200202003920039999631001980010208000020160000200392003911800211091010800001000000502000616262003680000102004020040200402004020040
8002420039150008442580010108000012800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502000616442003680000102004020040200402004020040
800242003915000402580010108000010800005064000005200202003920039999631001980010208000020160000200392003911800211091010800001000000502002216242003680000102004020040200402004020040
8002420039150001242580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000000502000416242003680000102004020040200402004020040
800242003915000402580010108000010800005064000005200202003920039999631001980010208000020160000200392003911800211091010800001000000502000416422003680000102004020040200402004020040
800242003915000402580010108000010800005064000005200202003920039999631001980010208000020160000200392003911800211091010800001000100502000216242003680000102004020040200402004020040
8002420039150001052580010108000010801125064000005200202003920039999631001980010208000020160000200392003911800211091010800001000000502000216442003680000102004020040200402004020040
8002420039150009792580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000000503350216242003680000102004020040200402004020040
800242003915000402580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000000502000416422003680000102004020040200402004020040
800242003915000822580010108000010800005064000010200202003920039999631001980010208000020160000200392003911800211091010800001000000502000216242003680000102004020040200402004020040