Apple M1 Microarchitecture Research by Dougall Johnson

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

EXT (vector, 8B)

Test 1: uops

Code:

  ext v0.8b, v0.8b, v1.8b, #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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073216111787100020382038203820382038
1004203716061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150117168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000021073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203716061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203716061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203716061168725100010001000264680201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  ext v0.8b, v0.8b, v1.8b, #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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000577101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150066819687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000157101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000817101161119791100001002003820038200382003820038
1020420037150044119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000667101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000160196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100000640216321978510000102003820038200382003820038
100242003715010545196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000103330661216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000103196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000631196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500361196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  ext v0.8b, v1.8b, 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)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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007103162219791100001002003820038200382003820038
102042003715006119687251017610010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000307102163319791100001002003820038200382003820038
1020420037150016619687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150014519687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715066119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150010719687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001001007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001001007102162219791100001002003820038200382003820038
1020420037150050919687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000012419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000008419687251001010100001010000502847680020018200372003718455318767100102010000202000020037200371110021109101010000100000000006402163219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000000000103196872510010101000010100005028476800200182003720037184442518767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
10024200371500000000046119687251001010100001010000502847680120018200372003718444318767101622010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  ext v0.8b, v8.8b, v9.8b, #3
  ext v1.8b, v8.8b, v9.8b, #3
  ext v2.8b, v8.8b, v9.8b, #3
  ext v3.8b, v8.8b, v9.8b, #3
  ext v4.8b, v8.8b, v9.8b, #3
  ext v5.8b, v8.8b, v9.8b, #3
  ext v6.8b, v8.8b, v9.8b, #3
  ext v7.8b, v8.8b, v9.8b, #3
  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)0308090b181e1f3f51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000000061258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511021611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010010000511011611200350800001002003920039200392003920039
802042003815000000046258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002010120091200902003920039
802042004915010100082428010010080093100800005806407740200192003820038997339996801002008009620016000020092200381180201100991001008000010000000511011621200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000010511011611200350800001002003920039200392003920039
802042003815000000082258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000000082258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000003511011611200350800001002003920039200392003920039
802042003815000009040258010010080093100800005006407800200602003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010002300511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304090e1e3f51inst 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)9faccfd0itlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000203925800101080000108000050640000120019200382003810005710018800102080000201600002003820038118002110910108000010050290017161682003580000102003920039200392003920039
800242003815000093925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100502000141617142003580000102003920039200392003920039
800242003815000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100502000391616192003580000102003920039200392003920039
8002420038150110010625800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502801171614172003580000102003920039200392003920039
80024200381501100852580010108000010800005064000012001920038200389996310018801182080000201600002003820038118002110910108000010050280110161792003580000102003920039200392003920039
800242003815000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100502000141617142003580000102003920039200392003920039
800242003815000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502000161610172003580000102003920039200392003920039
800242003815000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100502000141613172003580000102003920039200392003920039
800242003815000006225800101080000108000050640000120019200382003899963100188001020800002016014020038200381180021109101080000100502200171617172003580000102003920039200392003920039
800242003814900003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100502030171617142003580000102003920039200392003920039