Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNMP (vector, 8H)

Test 1: uops

Code:

  fmaxnmp v0.8h, v0.8h, v1.8h
  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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715012416872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxnmp v0.8h, v0.8h, v1.8h
  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)030b0f1e3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100001000710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000001440710116111979100100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000001260710116111979100100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100004000710116111979100100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000840710116111979100100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000030710116111979100100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100004000710116111979100100001002003820038200382003820038

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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500340196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640316221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500145196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxnmp v0.8h, v1.8h, v0.8h
  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)033f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715017719687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715027219687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371508219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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)9fc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371501061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844427187671001020100002020000200372003711100211091010100001000640216121978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxnmp v0.8h, v8.8h, v9.8h
  fmaxnmp v1.8h, v8.8h, v9.8h
  fmaxnmp v2.8h, v8.8h, v9.8h
  fmaxnmp v3.8h, v8.8h, v9.8h
  fmaxnmp v4.8h, v8.8h, v9.8h
  fmaxnmp v5.8h, v8.8h, v9.8h
  fmaxnmp v6.8h, v8.8h, v9.8h
  fmaxnmp v7.8h, v8.8h, v9.8h
  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)031e1f3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150120126258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051104161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)5f60696d6edispatch 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)9fa8a9acc2cdcfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150210392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000502051605520035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000502051606620035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000502041605620035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000502041605720035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000502061607620035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192011220038999631001880010208000020160000200382003811800211091010800001000000502041605520035080000102003920039200392003920039
800242003815000392580010108000010800005064000011200192003820038999631001880010208000020160000200382003811800211091010800001000000502051607620035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000502051605520035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001010000502041605420035080000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820087999631001880010208000020160000200382003811800211091010800001000000502051605420035080000102003920039200392003920039