Apple M1 Microarchitecture Research by Dougall Johnson

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

USHLL2 (4S)

Test 1: uops

Code:

  ushll2 v0.4s, v0.8h, #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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371601241686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371612611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  ushll2 v0.4s, v0.8h, #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)0308090b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500000001031968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002008620038200852003820038
102042003715500000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000210071011611197910100001002003820038200382003820038
102042003715500000001031968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000060071011611197910100001002003820038200382003820038
10204200371560000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
102042003715500000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000240071011611197910100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371560000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000060071011611197910100001002003820038200382003820038
102042003715500000001031968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371550000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b191e3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715500006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715600006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715500006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715500006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100003640216221978610000102003820038200382003820038
100242003714900006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715010006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500003846119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003716500006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100010640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  ushll2 v0.4s, v8.8h, #3
  ushll2 v1.4s, v8.8h, #3
  ushll2 v2.4s, v8.8h, #3
  ushll2 v3.4s, v8.8h, #3
  ushll2 v4.4s, v8.8h, #3
  ushll2 v5.4s, v8.8h, #3
  ushll2 v6.4s, v8.8h, #3
  ushll2 v7.4s, v8.8h, #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)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)9fa0a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057155029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151181160020035800001002003920039200392003920039
8020420038156029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100010011151180160020035800001002003920039200392003920039
8020420038156029318021010080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
8020420038155029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000611151180160020035800001002003920039200392003920039
80204200381550292580108411780008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100030011151180160020035800001002003920039200392003920039
8020420038156029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
8020420038156329258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151182160020077800001002003920039200392003920039
8020420038155029428010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100010011151180160020035800001002003920039200392003920039
8020420038155071258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100030011151180160020035800001002003920039200392003920039
8020420038156029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100020011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080e191e1f3f51inst 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)9fa0a1a7a8acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511550000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000040050200191619182003500080000102003920039200392003920039
80024200381550000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000010050200181621212003500080000102003920039200392003920039
800242003815500000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000018050200151618202003500080000102003920039200392003920039
8002420038155000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100004129050200191620202003500080000102003920039200392003920039
800242003815500000514258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000024165050200201618182003500080000102003920039200392003920039
8002420038155000001682580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000216050200191619202003500080000102003920039200392003920039
800242003815500000672580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000240050200181622192003500080000102003920039200392003920039
800242003815600000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000370050200201615212003500080000102003920039200392003920039
800242003815600000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000420050200201615192003500080000102003920039200392003920039
800242003815600000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000340050200191620192003500080000102003920039200392003920039