Apple M1 Microarchitecture Research by Dougall Johnson

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

NEG (vector, 16B)

Test 1: uops

Code:

  neg v0.16b, v0.16b
  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)03191e3f4e51inst 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
1004203716001031686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371510611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371600611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  neg v0.16b, v0.16b
  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)031e1f3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715518061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715078061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000907101161119791100001002003820038200382003820038
10204200371502550251196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715021061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715018061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150335261196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640416331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640341331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640349331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284789112001820037200371844303187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001000640316331978610000102003820038200382003820038
1002420037150002401968625100101010000101000050284752112001820037200371844303187671001020100002010000200372003711100211091010100001020640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  neg v0.16b, v8.16b
  neg v1.16b, v8.16b
  neg v2.16b, v8.16b
  neg v3.16b, v8.16b
  neg v4.16b, v8.16b
  neg v5.16b, v8.16b
  neg v6.16b, v8.16b
  neg v7.16b, v8.16b
  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)0308090b18191e1f3f51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500000031802925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000003425801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920091200902009020039
802042003815000000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132200192003820038998869989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050205160352003580000102003920039200392003920039
80024200381500013142580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050205160542003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050205160532003580000102003920039200392003920039
800242003814900392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050203160352003580000102003920039200392003920039
800242003815000622580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050205160352003580000102003920039200392003920039
80024200381500288392580010108000010800005064000002001920038201099996310018800102080000208000020038200381180021109101080000100050205160532003580000102003920039200392003920039
80024200381500222392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050203160552003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050205160532003580000102003920039200392003920039
80024200381500249392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050205160532003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050203160352019280000102003920039200392003920039