Apple M1 Microarchitecture Research by Dougall Johnson

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

SHL (vector, 8B)

Test 1: uops

Code:

  shl v0.8b, v0.8b, #3
  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
100420371515617216862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715010516862510001000100026452120182037203715713189510001000100020372037111001100001073116111786100020382038203820382038
1004203715018016752510001000100026452120182037203715713189510001000100020372037111001100000094116111786100020382038203820382038
1004203716025216862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715010316862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715011616862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715015616862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715027216862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020842037111001100000073116111786100020382038203820382038
1004203715021216862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  shl v0.8b, v0.8b, #3
  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)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)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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150032391968625101001001000010010000500284752102001820037200371842806187411010020010008200100082003720037111020110099100100100001000020201117170160019800100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842807187411010020010008200100082003720037111020110099100100100001000001117170160019801100001002003820038200382003820038
1020420037150045611968625101001001000010010000500284752102001820037200371842806187401010020010008200100082003720037111020110099100100100001000101117180160019801100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102005420037200371844307187411010020010008200100082003720037111020110099100100100001002001117170160019801100001002008720182200382008720038
102042003715000611968625101001001000010010000500284752102001820037200371842103187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842103187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842103187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842103187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500245481968625101001001000010010000500284752112001820037200371842103187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715010611968625101001001000010010000500284752102001820037200371842103187451010020010000200100002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010310006402162219786010000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001060006402162219786010000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001010006402162219786010000102003820038200382003820038
1002420037150611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010100006402162219842010000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001010006402162219786010000102003820038200382003820038
10024200371506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100017406402162219786010000102003820038200382003820038
100242003715061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001020006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shl v0.8b, v8.8b, #3
  shl v1.8b, v8.8b, #3
  shl v2.8b, v8.8b, #3
  shl v3.8b, v8.8b, #3
  shl v4.8b, v8.8b, #3
  shl v5.8b, v8.8b, #3
  shl v6.8b, v8.8b, #3
  shl v7.8b, v8.8b, #3
  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)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)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)9fa0a1a8acc2c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000025001115118116020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001001115118016020035800001002003920039200392003920075
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011201115118016020035800001002003920039200392003920039
8020420038150102925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000001115118016020035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001601115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa0a1a6a7a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150003039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000000502050616662003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000000502050516442003580000102003920039200392003920039
8002420038150006039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000000502050516662003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000002030502050516772003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000000502050516452003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000000030502050416562003580000102003920039200392003920039
8002420038149000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000003801680502050616452003580000102003920039200392003920039
8002420038150000029725800101080000108000050640000152001920038200389996310018800102080000208000020038200381180021109101080000100000500180502050516542003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001000001030502051517552003580000102003920039200392003920039
80024200381500000392580010108000010800005064000015200192003820038999631001880010208000020800002003820038118002110910108000010000054030502000516452003580000102003920039200392003920039