Apple M1 Microarchitecture Research by Dougall Johnson

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

SMAX (vector, 8H)

Test 1: uops

Code:

  smax 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)030b191e3f4e51inst 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
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715019611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715009611687251000100010002646802018203720371572318951000100020002037203711100110000673116111787100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150001491687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150001561687251000100010002646802018203720371572618951000100020002037203711100110000073116111787100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111853100020382038203820382038
1004203715000611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  smax 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)0308090b18191e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000121031968725101001001000010010000500284768002001820037200371842231874510100200100002102000020037200371110201100991001001000010000671011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000020611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010020071011611197910100001002003820038200382003820038
102042003715000100126119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000710116111979110100001002003820038200382003820038
10204200371500001001031968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000005361968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001201000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b181e3f4e51inst 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
1002420037150000066196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000082196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000084196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500000124196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500000726196872510010101000010100005028476800200182003720037184443187671001020100002021322200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  smax 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)03181e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001004071011611197910100001002003820038200382003820038
1020420037150000124196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000145196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720181111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000120196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000082196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242008415010611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002018020037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101015250284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003714900611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  smax v0.8h, v8.8h, v9.8h
  smax v1.8h, v8.8h, v9.8h
  smax v2.8h, v8.8h, v9.8h
  smax v3.8h, v8.8h, v9.8h
  smax v4.8h, v8.8h, v9.8h
  smax v5.8h, v8.8h, v9.8h
  smax v6.8h, v8.8h, v9.8h
  smax 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)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)9fa8cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150040258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511012161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011161120035800001002011420039201112003920039
8020420038150040258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011161120035800001002003920039200392003920039
8020420038150082258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001120019200382003899883999680100200800002001600002003820038118020110099100100800001000511011161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000120019200382003899733999680100200800002001600002003820038218020110099100100800001003511011161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001120019200382003899733999680100200800002001600002003820038118020110099100100800001000511011161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa0a1a6a8a9acc2cfd0d2icache miss (d3)d5d6d9dbddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000450392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200009160022200350080000102003920039200392003920039
8002420038150000210392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200002160062200350080000102003920039200392003920039
800242003815000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200002160022200350080000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201607782003820038118002110910108000010000000050200002160022200350080000102003920039200392003920039
8002420038150100120392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200002160052200350080000102003920039200392003920039
800242003815000000602580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200002160122200350080000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200102160062200350080000102003920039200392003920039
8002420038150000360392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050220002160022200350080000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200002160122200350080000102003920039200392003920039
80024200381500004740392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200002160066200350080000102003920039200392003920039