Apple M1 Microarchitecture Research by Dougall Johnson

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

UXTL2 (2D)

Test 1: uops

Code:

  uxtl2 v0.2d, v0.4s
  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)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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371508416862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715186116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uxtl2 v0.2d, 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): 2.0037

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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715606119686251010010010000100100005002850049120018200372003718428718741101002001000820010008200372003711102011009910010010000100031117170160019800100001002003820038200382003820038
102042003715506119686251010010010000100100005002847521020018200372003718428618741101002001000820010008200372003711102011009910010010000100001117180160019801100001002003820038200382003820038
102042003715506119686251010010010000100100005002847521020018200372003718428618740101002001000820010008200372003711102011009910010010000100101117180160019800100001002003820038200382003820038
102042003715506119686251010010010000100100005002847521020018200372003718428618741101002001000820010008200372003711102011009910010010000100031117170160019801100001002003820038200382003820038
102042003715506311968625101001001000010010000500284752102001820037200371842861874110100200100082001000820037200371110201100991001001000010001380007101161119791100001002003820038200382003820038
102042003715506119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100290007101161119791100001002003820038200382003820038
1020420037155061196862510100100100001001000050028475210200182003720082184213187451010020010000200100002003720037111020110099100100100001003300007101161119791100001002003820038200382003820038
102042003715506119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100600007101161119791100001002003820038200382003820038
1020420037155094196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000150007101161119791100001002003820038200382003820038
102042003715606119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100090007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080918191e3f4e51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000001210319686251001010100001010000502847521122001820037200371844331876710010201000020100002003720037111002110910101000010236402216221978610000102003820038200382003820038
100242003715000000103196862510010101000010100005028475211220018200372003718443318767100102010000201000020037200371110021109101010000101906402216221978610000102003820038200382003820038
1002420037150000012103196862510010101000010100005028475211220018200372003718443318767100102010000201000020037200371110021109101010000101396402216221978610000102003820038200382003820038
1002420037150000051137196862510010101000010100005028475211020018200372003718443318767100102010000201000020037200371110021109101010000101156400216221978610000102003820038200382003820038
100242003715000001217319686251001010100001010000502847521102001820037200371844731876710010201000020100002003720037111002110910101000010236402216341985810000102003820038200382003820038
100242003715000001261196862510010101000010100005028475210220018200372003718443318767100102010000201000020037200371110021109101010000101156400216221978610000102003820038200382003820038
100242003715000001217119686251001010100001010000502847521102001820037200371844331876710010201000020100002003720037111002110910101000010536402216221978610000102003820038200382003820038
100242003715000001210319686251001010100001010000502847521102001820037200371844331876710010201000020100002003720037111002110910101000010236402216221978610000102003820038200382003820038
100242003715000001210319686251001010100001010000502847521102001820037200371844331876710010201000020100002003720037111002110910101000010136402216221978610000102003820038200382003820038
100242003715000009176196862510010101000010100006628475211020018200372008518443318767100102010000201000020037200371110021109101010000101276400216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uxtl2 v0.2d, v8.4s
  uxtl2 v1.2d, v8.4s
  uxtl2 v2.2d, v8.4s
  uxtl2 v3.2d, v8.4s
  uxtl2 v4.2d, v8.4s
  uxtl2 v5.2d, v8.4s
  uxtl2 v6.2d, v8.4s
  uxtl2 v7.2d, v8.4s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 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)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)9fa0a1a8a9acc2c5branch mispredict (cb)cdcficache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057155103000120029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118021623200350800001002003920039200392003920039
802042003815510300000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118031633200350800001002003920039200392003920039
8020420038155103000300229258038910080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118031632200350800001002003920039200392003920039
802042003815510300000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118021632200350800001002003920039200392003920039
802042003815510300000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118031623200350800001002003920039200392003920039
8020420038155103000120029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000601115118031633200350800001002003920039200392003920039
802042003815510300000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118031623200350800001002003920039200392003920039
802042003815610300000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118031622200350800001002003920039200392003920039
80204200381551030001200162258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118011632200840800001002003920039200392003920039
802042003815510300000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000001115118021623200350800001002003920039200392003920039

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)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
800242003915501992580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050201716222003580000102003920039200392003920039
8002420038155039258001010803731080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010105020616632003580000102003920039200392003920039
8002420038156039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616262003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010205020316222003580000102003920039200392003920039
8002420038156060258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020216222003580000102003920039200392003920039
8002420038155039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010065020616632003580000102003920039200392003920039
80024200381551289258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020216222003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010035020216222003580000102003920039200392003920039
8002420038155039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020216662003580000102003920039200392003920039
80024200381550832580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000101805020216222003580000102003920039200392003920039