Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (zero, 4S)

Test 1: uops

Code:

  cmgt v0.4s, v0.4s, #0
  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)033f4e51inst 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
1004203715611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203716611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037151031686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.4s, v0.4s, #0
  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)0308091e3f4e51inst 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)9fa0a6a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150002761196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150002761196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500027611968625101001001000010010000500284752112001820037200371842117187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150000232196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500036536196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715001986119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150066119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500025119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150066119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150027961196862510010101000010100005028475212001820037200371844319187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150066119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715002946119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150008419686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmgt v0.4s, v8.4s, #0
  cmgt v1.4s, v8.4s, #0
  cmgt v2.4s, v8.4s, #0
  cmgt v3.4s, v8.4s, #0
  cmgt v4.4s, v8.4s, #0
  cmgt v5.4s, v8.4s, #0
  cmgt v6.4s, v8.4s, #0
  cmgt v7.4s, v8.4s, #0
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150632925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150152925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
80204200381502312925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920115
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150242925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
80204200381504442925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150212925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915001110392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050202163220035080000102003920039200392003920039
8002420038155000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050203163320035080000102003920039200392003920039
80024200381500120392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000050203163220035080000102003920039200392003920039
8002420038150000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050202162320035080000102003920039200392011320039
8002420038150000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050202163320035080000102003920039200392003920039
8002420038150000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050203163220035080000102003920039200392003920039
8002420038150030392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050203162320035080000102003920039200392003920039
8002420038150000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050203163320035080000102003920039200392003920039
80024200381500300392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050202163320035080000102003920039200392003920039
8002420038150000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000050202163320035080000102003920039200392003920039