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, 2D)

Test 1: uops

Code:

  uqadd 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)03080b1e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372200010325482510001000100039831330183037303724153289510001000200030373037111001100000073116212630100030383038303830383038
10043037220006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200061254825100010001000398313301830373037241532895100010002000303730371110011000010073116112630100030383038303830383038
10043037230006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300015625482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037220008425482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200061254825100010001000398313301830373037241532895100010002000303730371110011000033073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd 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)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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225156129548251010010010000100100005004277313030018300373003728265328745107252001000020020000300373003711102011009910010010000100187101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010037101161129634100001003003830038300383003830038
102043003722548612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a7a8acc2cfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000017182954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
100243003722400000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103008530085300383003830038
100243003722500000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
1002430037224000000009322954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
100243003722400000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038
100243003722400000000612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000000064002162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd 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)030b18191e1f3a3f4e51inst 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)9fa1a6a7a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000000210295482510100100100001001000050042773131300183003730182282653287451010020010000200200003003730037111020110099100100100001000000029980710011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000630710011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372828732874510100200100002002000030037300371110201100991001001000010000000810710011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
10204300372250000005362954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000810710011611296340100001003003830038300383003830038
10204300372250000005362954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000780710011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000150710011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000390710011611296340100001003003830038300383003830038

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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372411326129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000101000640216222963010000103003830038300383003830038
100243003724133010329548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000101000640216222963010000103003830038300383003830038
10024300372425410329548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000101300640216222963010000103003830038300383003830038
1002430037241037229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003724106129548251001010100001010000504277313130018302283003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003723306129539251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003723306129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037229096429548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722906129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722906129548251001010100001010000504277313030018302263003728287328767100102010000202000030037300371110021109101010000101000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd v0.2d, v8.2d, v9.2d
  uqadd v1.2d, v8.2d, v9.2d
  uqadd v2.2d, v8.2d, v9.2d
  uqadd v3.2d, v8.2d, v9.2d
  uqadd v4.2d, v8.2d, v9.2d
  uqadd v5.2d, v8.2d, v9.2d
  uqadd v6.2d, v8.2d, v9.2d
  uqadd 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391500231258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051106164420036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051104164520036800001002004020040200402004020040
8020420039150041258010010080000100800005006433040200202003920039997339997801002008000020016000020039200391180201100991001008000010000051105164520036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000151104165420036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051105165420036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051105165620036800001002004020040200402004020040
80204200391500611258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051104165420036800001002004020040200402004020040
8020420039150041258010010080000100803095006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051105165420036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051105165520036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051105164520036800001002004020040200402004020040

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010012950204164320036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050203164320036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000101050205165320036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050204163320036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050204164420036080000102004020040200402004020040
800242003915039402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050204164220036080000102004020040200402004020040
8002420039150271102580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050205165520036280000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050205165520036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100050205165520036080000102004020040200402004020040
8002420039150040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010012350204163420036080000102004020040200402004020040