Apple M1 Microarchitecture Research by Dougall Johnson

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

CLZ (vector, 8B)

Test 1: uops

Code:

  clz v0.8b, v0.8b
  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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371501051686251000100010002645211201820372037157131895100010001000203720371110011000073216111786100020382038203820382038
10042037160611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371501031686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371501261686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150821686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645210201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  clz v0.8b, v0.8b
  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)03080b18191e1f3f4e51inst 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)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000510611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
10204200371500000150611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420084150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
10204200841500000005361968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500285155302001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071021622197910100001002003820038200382003820038

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)9fa6a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000040640316331978610000102008620038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
100242003715000536196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
100242003715001561196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640316331978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100012000640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  clz v0.8b, v8.8b
  clz v1.8b, v8.8b
  clz v2.8b, v8.8b
  clz v3.8b, v8.8b
  clz v4.8b, v8.8b
  clz v5.8b, v8.8b
  clz v6.8b, v8.8b
  clz v7.8b, v8.8b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03070a1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048150010292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501102925801081008000810080020500640132020019200382003899776998980120200800322008003220038200382180201100991001008000010001511151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001001311151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100013511151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011411151181161120035800001002003920039200392003920039
80204200381501127292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a18191e1f3f51inst 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)5f60696d6edispatch 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000000962580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000020635020131613132003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000035035020161612162003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000020005020171613112003580000102003920039200392003920039
800242003815000000006025800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000320695020111613182003580000102003920039200392003920039
8002420038150000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020111611112003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000036035020131616122003580000102003920039200392003920039
8002420038150000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000035020161617152003580000102003920039200392003920039
8002420038150000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020171612182003580000102003920039200392003920039
8002420038150000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020151613132003580000102003920039200392003920039
8002420038150000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000000005020121615152003580000102003920039200392003920039