Apple M1 Microarchitecture Research by Dougall Johnson

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

ADD (vector, 16B)

Test 1: uops

Code:

  add 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)030b191e1f3f4e51inst 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)a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203716002940611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371501001561687251012101210002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037160090611687251000100010002646801201820372037157261895100010002000203720371110011000000073116111787100020382038203820382038
10042037160000611687251000100010002646801201820372037157231895100010002000203720731110011000000073116111787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  add 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)03090b1e3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500006119687451010010010000100100005002847680120018200372003718422318745101002001000020020000200372008411102011009910010010000100000090071011611197910100001002003820038200382003820038
10204200371490006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000093071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000300071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000069071011611197910100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000072071011611197910100001002003820038200862003820038
10204200371500002511968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150010611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150105196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640316221978510000102003820038200382003820038
1002420037150237196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037149149196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371501140196872510010101000010100005028476801200182003720037184443187671001020100002020324200372008411100211091010100001010640216221978510000102003820038200382003820038
100242003715061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001010640216221978510000102003820038200382003820038
100242003715082196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150149196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150821968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038
10024200371501238196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001020640216221978510000102003820038200382003820038
10024200371501296196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  add 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)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)696b6d6edispatch 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715008419687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100071011621197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420037150049519687251010010010000100100005002847680200180200372003718422318745101002001018020020000200372003711102011009910010010000100171011611197919100001002003820038200382003820038
1020420037150036419687251010010010000100100005002847680200180200372003718422718745102772001000020020000200372003711102011009910010010000100371011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200180200372003718422318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420037150021019687251010010010000100100005002847680200180200372003718425318745101002001000020020000200372003711102011009910010010000100071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa6a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150001031968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150030611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150002291968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402163219785010000102013320038200382003820038
10024200371491012901968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402163219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402163219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  add v0.16b, v8.16b, v9.16b
  add v1.16b, v8.16b, v9.16b
  add v2.16b, v8.16b, v9.16b
  add v3.16b, v8.16b, v9.16b
  add v4.16b, v8.16b, v9.16b
  add v5.16b, v8.16b, v9.16b
  add v6.16b, v8.16b, v9.16b
  add 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)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
8020420059150006825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102162120035800001002003920039200392003920039
80204200381500049225801001008000010080000500640000120019200382003899823999680100200800002001600002011620091118020110099100100800001001051101162120035800001002003920039200392003920039
80204200381500010325801001008000010080000500640000120019200382003899733999680100200800002001600002008620038118020110099100100800001001051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920190200392003920039
80204200381500025125801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500274025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101162120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502031622200350080000102003920039200392003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021622200350080000102003920039200392003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021622200350080000102003920039200392003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021622200350080000102003920039200392003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000001502031632200350080000102003920039200392003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021622200350080000102003920039200392003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021633200350080000102003920039200992003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021622200350080000102003920039200392003920039
80024200381500000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502031622200350080000102003920039200392003920039
80024200381550000003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021622200350080000102003920039200392003920039