Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSHL (immediate, scalar, H)

Test 1: uops

Code:

  uqshl h0, h0, #3
  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)033f4e51inst 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
10042037168216862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156116862510001000100026452112018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371512616862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037166116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156116862510001000100026452112054203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037166116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl h0, h0, #3
  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)0307080b18191e3a3f4e51inst 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)9fa0a1a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000506710011611197910100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000050153710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000710011611197910100001002003820038200382003820038
102042003715000000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100001503710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000009710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000009710011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000003710011611197910100001002003820038200382003820038
10204200371500000260611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000710011611197910100001002003820038200382003820038

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)9fa6a7cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000105196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000124196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001031640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uqshl h0, h8, #3
  uqshl h1, h8, #3
  uqshl h2, h8, #3
  uqshl h3, h8, #3
  uqshl h4, h8, #3
  uqshl h5, h8, #3
  uqshl h6, h8, #3
  uqshl h7, h8, #3
  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)03181e3f51inst 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)60696b6d6edispatch 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
80204200481500021925801081008000810080020500640132120019020038200389977699898012020080032200800322003820038118020110099100100800001000011151183164320035800001002003920039200392003920039
80204200381502602925801081008000810080020500640132020019020038200389977699898012020080132200800322003820038118020110099100100800001000611151184163320035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000311151184163320035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000011151184164320035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000011151184164320035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200190200382003899776998980120200800322008003220038200381180201100991001008000010037311151183163220035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000011151184162420035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000011151183163320035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000611151183163320035800001002003920039200392003920039
80204200381500031425801081008000810080020500640132020019020038200389977699898012020080032200800322003820038118020110099100100800001000011151183163420035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500000000006025800101080186108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000000502012166132003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000000050204161162003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200972003820038999631001880010208000020800002003820038118002110910108000010000000005020716462003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020716532003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050204161162003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020616642003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000305020516552003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820041318002110910108000010000000005020516462003580000102003920039200392003920039
800242003815000000090085258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000305020616452003580000102003920039200392003920039
8002420038150000000000942258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000010005020616542003580000102003920039200392003920039