Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINNMP (vector, 8H)

Test 1: uops

Code:

  fminnmp 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716024116872510001000100026468020182037203715723189510001000200020372037111001100003073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110002073116111787100020382038203820382038
10042037160611687251000100010002659632018203720371572318951000100020002037203711100110000673116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000973116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371503071687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fminnmp 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)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
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718425318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200732003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100097101161119791100001002003820038200382003820038
1020420037150072619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718433318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000217101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000157101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000040306402162219785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000150306402162219785010000102008620038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000220306402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000306402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671016020100002020000200372003711100211091010100001000020306402162219785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fminnmp 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)03081e1f3f4e51inst 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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000371011611198420100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000611968725101001091001210010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000371011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000371011611197910100001002003820038200382003820038

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)9fa6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200841501082196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010031050640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100100640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100030640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000102141140640216221978510000102003820038200382003820038
100242003715000611968725100221010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100160640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715600611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003714900611968725100101010000121030450284768020018200372003718444318767100102010000202000020037200371110021109101010000100100640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fminnmp v0.8h, v8.8h, v9.8h
  fminnmp v1.8h, v8.8h, v9.8h
  fminnmp v2.8h, v8.8h, v9.8h
  fminnmp v3.8h, v8.8h, v9.8h
  fminnmp v4.8h, v8.8h, v9.8h
  fminnmp v5.8h, v8.8h, v9.8h
  fminnmp v6.8h, v8.8h, v9.8h
  fminnmp 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)030708090a0b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150000000000084258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511041611200350800001002003920039200392003920039
8020420038150000000000040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011612200350800001002003920039200392003920039
80204200381500000000000149258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011612200350800001002003920039200392003920039
8020420038150000000000040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038150000000000063258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381540000000000200258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381500000000000705258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011622200840800001002003920039200392003920039
8020420038150000000000040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038150000000000040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011612200350800001002003920039200392003920039
80204200381490000000000314258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e3a3f51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420038150000528039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000021050207163320035280000102003920039200392003920039
8002420038150000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203163320035080000102003920039200392003920039
8002420038149000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203163320035080000102003920039200392003920039
8002420038150000006025800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203163320035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000003050207163420035080000102003920039200392003920039
800242003815000000131925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203163420035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203164720035080000102003920039200392003920039
8002420038150000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203167320035080000102003920039200392003920039
8002420038150000008125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050203163720035080000102003920039200392003920039
80024200381500000013425801041080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000050204163720035080000102003920039200392003920039