Apple M1 Microarchitecture Research by Dougall Johnson

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

SHADD (vector, 4H)

Test 1: uops

Code:

  shadd v0.4h, v0.4h, v1.4h
  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)a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371501931687251000100010002646802018203720371572318951000100020002037203711100110000673116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000973116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  shadd v0.4h, v0.4h, v1.4h
  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)0318191e1f3f4e51inst 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)9fa0a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500017706119687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000030710001161119791100001002003820038200382003820038
10204200371500012015619687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710001161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710001161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710001161119791100001002003820038200382003820038
102042003715004006119687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000219670710001161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680102001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710501161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680052001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710501161119791100001002003820038200382003820038
1020420037150002706119687251010010010000100100005002847680152001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710001161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680152001820037200371842231874510100200100002002000020037200371110201100991001001000010000000710501161119791100001002003820038200382003820038
10204200371500092646119687251010010010000100100005002847680152001820037200371842231874510100200100002002000020037200371110201100991001001000010001000710501161119791100001002003820038200382003820038

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)9fa6a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500120104196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500001117196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216121978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150000726196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001020640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500357061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  shadd v0.4h, v1.4h, v0.4h
  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)0308090b18191e1f3f4e51inst 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)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000154061196872510100100100001001045650028476801200182013320085184223187451010020010000200200002003720037111020110099100100100001000010071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150000009061196742510100100100001001000050028476801200182003720037184443187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000000124196872510100100100001001000050028476801200182003720037184223187451010020010000200203302003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000021061196872510100100100001001000050028489631200182003720037184223187451010020010000200200002003720037111020110099100100100001000013071021611197910100001002003820038200382003820038
10204201331500004039061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611199340100001002003820038200382003820038
1020420037150100000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011612197910100001002003820038200382003820038
1020420084150000000061196872510100100100001001000050028476800200182003720037184293187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150000000061196872510100100100001001060850028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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
10024200371500000000726196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006404162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000010270061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000009061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000012061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000036061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010104565028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000926461196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  shadd v0.4h, v8.4h, v9.4h
  shadd v1.4h, v8.4h, v9.4h
  shadd v2.4h, v8.4h, v9.4h
  shadd v3.4h, v8.4h, v9.4h
  shadd v4.4h, v8.4h, v9.4h
  shadd v5.4h, v8.4h, v9.4h
  shadd v6.4h, v8.4h, v9.4h
  shadd v7.4h, v8.4h, v9.4h
  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)030418191e3f51inst 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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381501000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511021611200350800001002003920039200392003920039
8020420038150000213252580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000300511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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
800242004815000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020616982003580000102003920039200392003920039
80024200381490354392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020816862003580000102003920039200392003920039
80024200381500333392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020716682003580000102003920039200392003920039
80024200381490252392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020916872003580000102003920039200392003920039
800242003815000392580010108009210800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020716692003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020616682003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020916862003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005020716682003580000102003920039200392003920039
8002420038150001042580010108000010800005064000012001920038200389996310018800102080132201600002003820038118002110910108000010005020716682003580000102003920039200392003920039
800242003815003033925800101080000108000050640000020019200382003810011310018800102080000201600002003820038118002110910108000010005020916782003580000102003920039200392003920039