Apple M1 Microarchitecture Research by Dougall Johnson

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

FMIN (scalar, S)

Test 1: uops

Code:

  fmin s0, s0, s1
  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)03070a3a3f4e51inst 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000077316441787100020382038203820382038
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000377416441787100020382038203820382038
10042037161126816872510001000100026468020182037203715723189510001000200020372037111001100000075577416441787100020382038203820382038
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000077416441787100020382038203820382038
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000077416441787100020382038203820382038
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000077416441787100020382038203820382038
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000077416441787100020382038203820382038
100420371611268168725100010001000264680201820372037157231895100010002000203720371110011000000377316441787100020382038203820382038
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000077416441787100020382038203820382038
100420371511268168725100010001000264680201820372037157231895100010002000203720371110011000000077416441787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmin s0, s0, s1
  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)03083f4e51inst 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)696b6d6edispatch 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)9fa6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715009019687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150017019687251010010010000100100005002847680200180200372003718422318745101002001016420020000200372003711102011009910010010000100003071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150012319687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001802003720037184223187451010020010000200200002003720037111020110099100100100001000000710116111979126100001002003820038200382003820038
102042003715009419687251010010010000100100005002847680200180200862003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037149017419687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197912100001002003820038200382003820038
1020420037150010319676431013210010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011621197918100001002003820038200382003820038
1020420037150110319687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03070b18191e3f4e51inst 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)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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000001031968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100066402162219785210000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100122010000202000020037200371110021109101010000100106402164419785010000102003820038200382003820085
100242003715010000821968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100122010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000001181968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100106402162219785010000102003820038200382003820038
1002420037150000005361968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100006402162219785210000102003820038200382003820038
100242003715000000821968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100106402162219787210000102003820038200382003820038
1002420037150000001241968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001802003720037184440318767100102010000202000020037200371110021109101010000100106402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmin s0, s1, s0
  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)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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715002631968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715001471968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382008620038
102042003715004051968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715003871968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715004871968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080a0b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000393061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000069061196672510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003714900000012061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184447187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000024061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000225061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010121000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmin s0, s8, s9
  fmin s1, s8, s9
  fmin s2, s8, s9
  fmin s3, s8, s9
  fmin s4, s8, s9
  fmin s5, s8, s9
  fmin s6, s8, s9
  fmin s7, s8, s9
  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)030b1e3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200561500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511031611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500940258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011610200350800001002003920039200392003920039
80204200381500061258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815001240258010010080093100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815001240258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802021009910010080000100000511011611200350800001002003920039200392003920039
802042003815002440258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa8accfd0d2d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715001239258001010800001080000506400001020019200382003899963100188001020800002016000020038200381180021109101080000100050200021600024200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200041600042200350080000102003920039200392003920039
80024200381501039258001010800001080000506400001120019200382003899963100188001020800002016000020038200381180021109101080000100050200021600024200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200041600024200350080000102003920039200392003920039
8002420038155033514258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200021600077200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200041600042200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200041600042200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200021600067200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200041600044200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200021600043200350080000102003920039200392003920039