Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINP (vector, 16B)

Test 1: uops

Code:

  uminp v0.16b, v0.16b, v1.16b
  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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116874210001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371636116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uminp v0.16b, v0.16b, v1.16b
  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)031e3a3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768005200182003720037184296187411010021210008200200162003720037111020110099100100100001001798611171800160019802100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768010200182003720037184297187401010020010008200200162003720037111020110099100100100001000011171700160019801100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184296187411010020010008200200162003720037111020110099100100100001000011171750160019802100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768010200182003720037184296187411010020010008200200162003720037111020110099100100100001000011171750160019802100001002003820038200382003820038
102042003715030611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768010200182003720037184223187451010020010000200200002003720037111020110099100100100001003000071001161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071001161119791100001002003820038200382003820038
10204200371501470611968725101001001000010010000500284768005200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071051161119791100001002003820038200382003820038
10204200371502730611968725101001001000010010000500284768005200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071051161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768000200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071051161119791100001002003820038200382003820038

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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150276119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150246119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150072619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003714906119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150216119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715096119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uminp v0.16b, v1.16b, v0.16b
  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)03090b18191e1f3f4e51inst 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)9fa0a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000611968725101001311000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820180
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010002000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000030071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000200198300006403162319785110000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476802001820085200371844431876710010201000020200002003720085111002110910101000010000190300006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100221091010100001000000000006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000030300006402162219785010000102003820038200382003820038
10024200371500000000010319687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000300006402162219785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000010300006402162219785010000102003820038200382003820038
10024200371500000016288168019687251001010100001010000502847680200182003720131184443187671016220100002020000200372003721100211091010100001020010000006402162219785010000102003820038200382003820038
1002420037150000000008219687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000030600006402162219785010000102003820038200382003820038
10024200371500000012006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000300006402162219785010000102008520038200382003820038
10024200371500000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000470000006402242219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uminp v0.16b, v8.16b, v9.16b
  uminp v1.16b, v8.16b, v9.16b
  uminp v2.16b, v8.16b, v9.16b
  uminp v3.16b, v8.16b, v9.16b
  uminp v4.16b, v8.16b, v9.16b
  uminp v5.16b, v8.16b, v9.16b
  uminp v6.16b, v8.16b, v9.16b
  uminp v7.16b, v8.16b, v9.16b
  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)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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021611200350800001002003920039200392003920039
80204200381500402580125125800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511221611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100002103511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399958010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000100511011611200350800001002003920039200392003920039

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)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)9fa6a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815103925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
8002420038150081025800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100189502000116112003580000102003920039200392003920039
80024200381500132625800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100042502000116112003580000102003920039200392003920039
8002420038150070425800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000502000116112003580000102003920039200392003920039
8002420038150042325800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010050502052116112003580000102003920039200392003920039