Apple M1 Microarchitecture Research by Dougall Johnson

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

ZIP1 (vector, 8H)

Test 1: uops

Code:

  zip1 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)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
100420371566116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371696116872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip1 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)030818191e1f3a3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371560000002291968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
10204200371550000001091968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
1020420037156000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371560009001491968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037155000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550000005251968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)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
100242003715500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100087640216221978510000102003820038200382003820038
1002420037155001311968725100101010000101000050284768002001820037200371844471878610010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100149640216221978510000102003820038200382003820038
100242003716000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715600611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010010640216221978510000102003820038200382003820038
10024200371550061196872510010101000010100005028476801200182003720037184583187671001020100002020000200372003711100211091010100001000138640216221978510000102003820038200382003820038
100242003715600611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip1 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)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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550001087196872510100100100001001000050028476800200182003720037184227187451010020010000200200002003720037111020110099100100100001000000007102161119791100001002003820038200382003820038
1020420037155000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037161001261196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000001307101161119791100001002013420086200862003820038
102042003715500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715600061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371550010861196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003716100061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550012719687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100003640216231978510000102003820038200382003820038
100242003715500184619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100100640216231978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037156006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100100640216221978510000102003820038200382003820038
10024200371551010419687251001010100121010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037161006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037155006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037156006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  zip1 v0.8h, v8.8h, v9.8h
  zip1 v1.8h, v8.8h, v9.8h
  zip1 v2.8h, v8.8h, v9.8h
  zip1 v3.8h, v8.8h, v9.8h
  zip1 v4.8h, v8.8h, v9.8h
  zip1 v5.8h, v8.8h, v9.8h
  zip1 v6.8h, v8.8h, v9.8h
  zip1 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)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
802042005815504025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
802042003815504025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161220035800001002003920039200392003920039
802042003815604025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815504025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815504025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815504025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815604025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815534025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815506125801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815504025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f5051inst 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)9fa1a8accfd0d5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048155067025800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005032041601120035080000102003920039200392003920039
8002420038156039025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000102005034011601120035080000102003920039200392003920039
8002420038156067025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005034011601120035080000102003920039200392003920039
80024200381550609025800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005034011601120035280000102003920039200392003920039
8002420038156039025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005034011601120035080000102003920039200392003920039
80024200381552139025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005034051605120035080000102003920039200392003920039
8002420038155039025800121280000128000060640000020019200382003899963100188001020800002016000020038200381180021109101080000100005034011605520035080000102003920039200392003920039
8002420038155067025800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005034011601120035080000102003920039200392003920039
8002420038155039025800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005034011605520035080000102003920039200392003920039
8002420038155081025800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100005032011601120035080000102003920039200392003920039