Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHLU (vector, 16B)

Test 1: uops

Code:

  sqshlu v0.16b, v0.16b, #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)0308191e3f4e51inst 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)a0a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000611686251000100010002645212018203720371571318951000100010002037203711100110000000073116111786100020382038203820382038
1004203715000611686251000100010002645212018203720371571318951000100010002037203711100110000000073116111786100020382038203820382038
1004203715000611686251000100010002645212018203720371571318951000100010002037203711100110000100073116111786100020382038203820382038
1004203715000611686251000100010002645212018203720371571318951000100010002037203711100110000000073116111786100020382038203820382038
1004203715006611686251000100010002645212018203720371571318951000100010002037203711100110000000073116111786100020382038203820382038
10042037160003821686251000100010002645212018203720371571318951000100010002037203711100110000000073116111786100020382038203820382038
10042037150003101686251000100010002645212018203720371571318951000100010002037203711100110000000073116111786100020382038203820382038
1004203715000841686251000100010002645212018203720371571318951000100010002037203711100110000120073116111786100020382038203820382038
1004203715000611686251000100010002645212018203720371571318951000100010002037203711100110000000073116111786100020382038203820382038
10042037150006116862510001000100026452120182037203715713189510001000100020372037111001100000012073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshlu v0.16b, v0.16b, #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)030b1e1f3a3f4e51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000011219686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382008620038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100003071001611197910100001002003820038200382003820038
102042003715000016119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100009071011611197910100001002003820038200382003820038
102042003715001478806119686251010010010000100100005002847521020018200372003718421318745101002001000020010168200372003711102011009910010010000100000071011631197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b191e3f4e51inst 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)696d6edispatch 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003714910012419686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001002119686404164419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006405164419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006405164419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006403164419786010000102003820038200382003820086
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006403164419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006403163419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006405164419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006404164419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006404164419786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100006403164419786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshlu v0.16b, v8.16b, #3
  sqshlu v1.16b, v8.16b, #3
  sqshlu v2.16b, v8.16b, #3
  sqshlu v3.16b, v8.16b, #3
  sqshlu v4.16b, v8.16b, #3
  sqshlu v5.16b, v8.16b, #3
  sqshlu v6.16b, v8.16b, #3
  sqshlu v7.16b, v8.16b, #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)0308090b18191e1f3a3f51inst 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)9fa7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000000300029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500000000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381510000000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815000000000377258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815000000000414258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500000000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815000000000599258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815000000000434258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500000000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
80204200381500000000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150003925800101080000108000050640000120019200382003899960310018800102080000208000020038200381180021109101080000100050201416462003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020800002003820038118002110910108000010005020816652003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899960310018800102080000208000020038200381180021109101080000100050221016452003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899960310018800102080000208000020038200381180021109101080000100050201116662003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996031001880010208000020800002003820038118002110910108000010005020816652003580000102003920039200392003920039
8002420038150005142580010108000010800005064000002001920038200389996031001880010208000020800002003820038118002110910108000010005020916552003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020800002003820038118002110910108000010005020916452003580000102003920039200392003920039
800242003815000392580103108000010800005064000002001920038200389996031001880010208000020800002003820038118002110910108000010005020916562003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020800002003820038118002110910108000010005020916662003580000102003920039200392003920039
80024200381500012325800101080000108000050640000020019200382003899960310018800102080000208000020038200381180021109101080000100050201216662003580000102003920039200392003920039