Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDW2 (vector, 2D)

Test 1: uops

Code:

  saddw2 v0.2d, v0.2d, v1.4s
  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
1004203715011716872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001012100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371508716872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371536116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  saddw2 v0.2d, v0.2d, v1.4s
  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)03181e3f4e51inst 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)9fa8a9accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150001471968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000020157109911621197910100001002003820086200382003820038
102042003715000611968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000007109911611197910100001002003820038200382003820038
102042003715000841968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000037100011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000007109411611197910100001002003820086200382003820038
10204200371501011451968761101161061000010010000500284768019200182008620037184227187621010020010000200200002003720037111020110099100100100001000007109411611197910100001002003820038200382003820038
10204200371490010161968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000037109411611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000007109411611197910100001002003820038200382003820038
10204200371500121701968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000097109411611197910100001002003820038200382003820038
102042003715000841968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001001007109411611197910100001002003820038200382003820038
1020420037150001871968725101001001000010010000500284768019200182003720037184223187451010020010000200200002003720037111020110099100100100001000007109411611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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
10024200371504061968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006406162219785010000102003820038200382003820038
1002420037150611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382013320038
10024200371503711968743100241010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037149611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371501241968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371498331968725100101010000101000050284806602001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  saddw2 v0.2d, v1.2d, v0.4s
  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)030a181e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102252219791100001002003820038200902003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000124196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000251196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000124196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221985110000102003820038200382003820038
100242003715000103196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  saddw2 v0.2d, v8.2d, v9.4s
  saddw2 v1.2d, v8.2d, v9.4s
  saddw2 v2.2d, v8.2d, v9.4s
  saddw2 v3.2d, v8.2d, v9.4s
  saddw2 v4.2d, v8.2d, v9.4s
  saddw2 v5.2d, v8.2d, v9.4s
  saddw2 v6.2d, v8.2d, v9.4s
  saddw2 v7.2d, v8.2d, v9.4s
  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)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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100990100100800001000051105161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002008020097200389973399968010020080000200160000200382003811802011009920022100100800001000051101161120035800001002003920039200392003920039
8020420038150082258010010080000100800005006400002001920038200389973399968010020080099200160000200382003811802011009920022100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100990100100800001000351101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100990100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100990100100800001000051101161220035800001002003920039200392003920039
802042009015004025801001008000010080000500640000200192003820038997339996801002008000020016000020038201001180201100990100100800001000051101171120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100990100100800001000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100990100100800001000051101161120035800001002003920039200392003920039
8020420038150042025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100990100100800001000051101161120035800001002003920039200392003920039

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)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)9fa8cfd2d5d6daddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100502002516071120035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010050200916091120035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020081608620035080000102003920039200392003920039
80024200381500704258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010050200816010720035080000102003920039200392003920039
800252003815019839258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010050200816097200352080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010050200616071020035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010050770111608820035080000102003920087200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020071605720035080000102003920039200392003920039
800242003815003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020061604620035080000102003920039200392003920039
8002420038150039258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010050200516071020035080000102003920039200392003920039