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, 2S)

Test 1: uops

Code:

  fminnmp v0.2s, v0.2s, v1.2s
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116762510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fminnmp v0.2s, v0.2s, v1.2s
  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)9fa6accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715569661196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000073711611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510125100100001251000050028476800200182003720037184223187441010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187441012520010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187631025920010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003716049261196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000062628476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715046861196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371504261196872510100100100001001000050028476800200182003720037184223187441010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e1f3f4e51inst 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
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640416661978510000102003820038200382003820038
10024200371500222061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640516551978510000102003820038200382003820038
10024200371500483061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640616651978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640616651978510000102003820038200382003820038
1002420037150012061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640516561978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640516551978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640516651978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640516651978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640416661978510000102003820038200382003820038
100242003715009061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640516661978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fminnmp v0.2s, v1.2s, v0.2s
  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)6061696d6edispatch 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)9fa6a7a8a9accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715018611968725101001001000010010000500284768010200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021161119791100001002003820038200382003820038
102042003715015611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021161119791100001002003820038200382003820038
10204200371506611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000010071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768010200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
102042003715001031968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
102042003715027611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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
1002420037150000000611968725100101010000101000050284768012001820037200371844473187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000750611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000821968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037149000000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037149000000611968725100101010000101000050284768012001820084200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000690611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000330611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844403187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fminnmp v0.2s, v8.2s, v9.2s
  fminnmp v1.2s, v8.2s, v9.2s
  fminnmp v2.2s, v8.2s, v9.2s
  fminnmp v3.2s, v8.2s, v9.2s
  fminnmp v4.2s, v8.2s, v9.2s
  fminnmp v5.2s, v8.2s, v9.2s
  fminnmp v6.2s, v8.2s, v9.2s
  fminnmp v7.2s, v8.2s, v9.2s
  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)030a18191e1f3f51inst 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)6061696d6edispatch 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150000004025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100005110002161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100005110701161120035800001002003920039200392003920039
8020420038150000904025801001008000010080000500640000002001920038200389973399968010020080000200160000200382003811802011009910010080000100005110071161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000172001920038200389973399968010020080000200160000200382003811802011009910010080000100035110771161120035800001002003920039200392003920039
80204200381500001504025801001008000010080000500640000172001920038200389973399968010020080000200160000200382003811802011009910010080000100005110771161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000172001920038200389973399968010020080000200160000200382003811802011009910010080000100005110771161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000002001920038200389973399968010020080000200160000200382003811802011009910010080000100135110701162120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000072001920038200389973399968010020080000200160000200382003811802011009910010080000100005110771161120035800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100005110771161120035800001002003920039200392003920039
8020420038150000144092225801001008000010080000500640000172001920038200389973399968010020080000200160000200382003811802011009910010080000100005110771161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070f1e3f51inst 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)6061696d6edispatch 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)9fa8cfd0d2d5d6dbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500016839258001010800001080000506400000520019200382003899963100188001020800002016000020038200381180021109101080000100502050116011200350080000102003920039200392003920039
8002420038156003339258001212800001080000606400000520019200382003899963100188001220800002016000020038200381180021109101080000100502000116011200350080000102003920039200392003920039
800242003815010039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100502050116011200350080000102003920039200392003920039
8002420038150009210258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100502050116011200350080000102003920039200392003920039
80024200381500043839258001010800001080000506400000520019200382003899963100188001020800002016000020038200381180021109101080000100502051116111200350080000102003920039200392003920039
800242003815000039258001010800001080000506400001020019200382003899963100188001020800002016000020038200381180021109101080000100502000116011200350080000102003920039200392003920039
8002420038150000514258001010800001080000506400001020019200382003899963100188001020800002016000020038200381180021109101080000100502051116011200350080000102003920039200392003920039
800242003815000339258001010800001080000506400000520019200382003899963100188001020800002016000020038200381180021109101080000100502000116011200350080000102003920039200392003920039
800242003815000039258001010800001080000506400000520019200382003899963100188001020800002016000020038200381180021109101080000100502051116011200350080000102003920039200392003920039
800242003815000039258001010800001080000506400001520019200382003899963100188001220800002016000020038200381180021109101080000100502000116011200350080000102003920039200392003920039