Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDP (vector, 2S)

Test 1: uops

Code:

  addp v0.2s, v0.2s, v1.2s
  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)03081e3f4e51inst 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715002611687251000100010002646801201820372037157231895100010002000203720371110011000073216111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371600611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371600611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
1004203716048611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  addp v0.2s, v0.2s, v1.2s
  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)03081e3f4e51inst 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
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001001071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001001071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000611968725101671001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001006071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768013200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768013200182003720037184223187451010020010000200200002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010304500284768000200182003720037184223187451010021210000200200002003720037111020110099100100100001005071031161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500124196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100044300640216221978510000102003820038200852003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
1002420037149084196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500168196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
1002420037150094196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500103196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  addp v0.2s, v1.2s, v0.2s
  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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150074119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715008419687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251012910010012100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010020071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200183200372003718422318745101002001000020020000200372003711102011009910010010000100530071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500841968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715002351968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715001911968725100101010000101000050284768020018200372008418444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500841968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162319785010000102003820038200382003820038
10024200371500821968725100101010000101000050284768020018200372003718444318767101632010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100906402162319785010000102003820038200382003820038
100242003715001451968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  addp v0.2s, v8.2s, v9.2s
  addp v1.2s, v8.2s, v9.2s
  addp v2.2s, v8.2s, v9.2s
  addp v3.2s, v8.2s, v9.2s
  addp v4.2s, v8.2s, v9.2s
  addp v5.2s, v8.2s, v9.2s
  addp v6.2s, v8.2s, v9.2s
  addp v7.2s, v8.2s, v9.2s
  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)03090b1e1f3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150000063258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511021611200350800001002003920189200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920086
8020420038150000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
8020420038150000061258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000511021611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2cfd2d5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020041662420035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020021652420035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020041654220035080000102003920039200392003920039
80024200381500000000602580010108000010800005064072412001920038200389996310018800102080000201600002003820038118002110910108000010000000005020041652420035080000102003920039200392003920039
800242003815000000003772580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020021652420035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020041652420035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020041662520035080000102003920039200392003920039
80024200381500000000622580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020041654420035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020031654220035080000102003920039200392003920039
800242003815000000005142580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020041652420035080000102003920039200392003920039