Apple M1 Microarchitecture Research by Dougall Johnson

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

CLS (vector, 16B)

Test 1: uops

Code:

  cls v0.16b, v0.16b
  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)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
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571319071000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cls v0.16b, 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)03080b1e1f3f4e51inst 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
1020420037150000061196864510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611198310100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000536196862510100113100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000710116111979112100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184218187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820084
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000168196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000168196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500661968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715001241968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715001261968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715004411968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715001701968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cls v0.16b, v8.16b
  cls v1.16b, v8.16b
  cls v2.16b, v8.16b
  cls v3.16b, v8.16b
  cls v4.16b, v8.16b
  cls v5.16b, v8.16b
  cls v6.16b, v8.16b
  cls v7.16b, v8.16b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03091e3f51inst 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)72scheduler 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)9fc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015025164278011610080016100800285006401960200282004920048997609998680128200800382008003820048200481180201100991001008000010022251282231120046800001002005020049200482004820050
80204200481500075278010010080000100800005006400000200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202252220044800001002004820048200482004820048
80204200471500075278010010080000100800005006400001200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048
80204200471500075278010010080000100800005006400001200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048
802042004715000740278010010080000100800005006400001200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048
80204200471500075278010010080000100800005006400001200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048
80204200471500075278010010080000100800005006400000200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048
80204200471500075278010010080000100800005006400001200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048
8020420047150001195278010010080000100800005006400001200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048
80204200471500075278010010080000100800005006400001200282004720047997106999380100200800002008000020047200471180201100991001008000010011151202242220044800001002004820048200482004820048

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020121671120035080000102003920039200392003920039
80024200381500000004192580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050201116111120035080000102003920039200392003920039
8002420038150000015039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020111611720035080000102003920039200392003920039
80024200381500000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000000502071671120035080000102003920039200392003920039
80024200381500000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000000502071611720035080000102003920039200392003920039
8002420038150000000704258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020111611720035080000102003920039200392003920039
800242003815000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020916111120035080000102003920039200392003920039
8002420038150000015039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020111611720035080000102003920039200392003920039
800242003815000000042258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020111611720035080000102003920039200392003920039
8002420038150000000229258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020716111120035080000102003920039200392003920039