Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLE (vector, zero, 4S)

Test 1: uops

Code:

  fcmle 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)031e3f4e51inst 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
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073216111786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371601031686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715162611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmle 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)9fa0accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150110251196862510100100100001001000060828475210200182003720037184213187451010020610000200100002003720037111020110099100100100001002371011611197910100001002003820038202312003820038
102042003715000285103196862510100130100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000186103196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071021611197910100001002003820038200382003820038
102042003715000061196862510100100100001001015259228475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500023761196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000661196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150002761196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150002161196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002008720038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184217187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3a3f4e51inst 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
1002420037150004506119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150002706119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150002106119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150008406119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000072619686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmle v0.4s, v8.4s, #0
  fcmle v1.4s, v8.4s, #0
  fcmle v2.4s, v8.4s, #0
  fcmle v3.4s, v8.4s, #0
  fcmle v4.4s, v8.4s, #0
  fcmle v5.4s, v8.4s, #0
  fcmle v6.4s, v8.4s, #0
  fcmle 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)0318191e3f51inst 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)9fa9c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000122925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920086
802042003815000635225802121008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
80204200381501162925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180161120035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
802042003815000242925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180170020035800001002003920039200392003920039
80204200381500020112425801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
80204200381500032925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
802042003815000122925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039

1000 unrolls and 10 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420124150333602580010108000010800005064000012001920038200389996310018801092080000208000020038200381180021109101080000100005020221611142003580000102003920039200392003920039
8002420038150153925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050207165102003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050209169112003580000102003920039200392003920039
800242003815006025800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050201016962003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631004680010208000020800002003820038118002110910108000010000502010161072003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000502010167102003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050209161072003580000102003920039200392003920039
800242003815002292580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020516772003580000102003920039200392003920039
800242003815015392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020716582003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020816872003580000102003920039200392003920039