Apple M1 Microarchitecture Research by Dougall Johnson

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

ZIP2 (vector, 2D)

Test 1: uops

Code:

  zip2 v0.2d, v0.2d, v1.2d
  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
1004203716024716872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
1004203715126116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203716012216872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110001373216221787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip2 v0.2d, v0.2d, v1.2d
  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)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)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000206071011611197910100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371610611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715507261968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715512611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b191e3a3f4e51inst 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)9fa6a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000611968725100101010000101015050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000001031968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403162219785010000102003820038200382003820038
10024200371500000611968725100101210000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201017220200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010210006403162219785210000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip2 v0.2d, v1.2d, v0.2d
  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)03080a0b18191e1f3a3f4e51inst 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
1020420037156000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000003071011611197910100001002003820038200382003820038
1020420037155000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037156000000006119687251010010010012100101525002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371560000000053619687251010010010000100100005002847680020054200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000003071011611197910100001002003820038200382003820038
1020420037156000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100002000071011611197910100001002008520038200852003820038
1020420037155100000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b0f1e3f4e51inst 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
10024200371560000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371550000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371550000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371560000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371560000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715500001031968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371550000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371550000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010036402162219785010000102003820038200382003820038
10024200371550000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715500006361968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  zip2 v0.2d, v8.2d, v9.2d
  zip2 v1.2d, v8.2d, v9.2d
  zip2 v2.2d, v8.2d, v9.2d
  zip2 v3.2d, v8.2d, v9.2d
  zip2 v4.2d, v8.2d, v9.2d
  zip2 v5.2d, v8.2d, v9.2d
  zip2 v6.2d, v8.2d, v9.2d
  zip2 v7.2d, v8.2d, v9.2d
  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)030708090b18191e1f3f51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038156000000006825801001008000010080000500640000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511031611200350800001002003920039200392003920039
8020420038155000100004025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
802042003815500000000230258010010080000100800005006400001020019200382003899733999680100200800002001600002003820038118020110099100100800001000000780511011611200350800001002003920039200392003920039
80204200381560000000040258010010080000100800005006400001020019200382003899733999680100200800002001600002003820038118020110099100100800001000000120511011611200350800001002003920039200392003920039
8020420038155000000304025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100000060511011611200350800001002003920039200392003920039
8020420038156000000004025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100000060511011611200350800001002003920039200392003920039
8020420038155100100304025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100001060511011611200350800001002003920039200392003920039
8020420038156000000004025801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100000030511011611200350800001002003920039200392003920039
8020420038155000000008225801001008000010080000500640000102001920038200389973399968010020080000200160000200382003811802011009910010080000100000030511011611200350800001002003920039200392003920039
8020420038155000000004025801001008000010080000500640000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000030511011611200350800001002003920039200392003920039

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)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)9fa1a6a8acc5cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155081258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502050916962003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502000616992003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502000616692003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502000916962003580000102003920039200392003920039
8002420038155939258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502000916962003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001020000502000716792003580000102003920039200392003920039
8002520038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502003916692003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000230502000916962003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502000716962003580000102003920039200392003920039
8002420038155039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502000916962003580000102003920039200392003920039