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, S)

Test 1: uops

Code:

  uqshl s0, s0, #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)0308181e3f4e51inst 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
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037151006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100011073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100002473116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371500126116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000673116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uqshl s0, s0, #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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000000001031968625101001001000010010000500284878520018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820181200852003820086
102042003715000010005621968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611198590100001002003820038200382013320038
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371490000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000003071011611197910100001002003820038200862003820038
10204200371500000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150008219686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150008219686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037149006119686251001010100001010152502847521020018200372003718443318767100102010000201000020037200371110021109101010000103640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uqshl s0, s8, #3
  uqshl s1, s8, #3
  uqshl s2, s8, #3
  uqshl s3, s8, #3
  uqshl s4, s8, #3
  uqshl s5, s8, #3
  uqshl s6, s8, #3
  uqshl s7, s8, #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)6061696d6edispatch 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)9fa8acc5branch mispredict (cb)cdcfd0d2d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200501500232258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
80204200381500138258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
80204200381500138258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
80204200381500389258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321520019200382003899770699898012020080032200800322003820038118020110099100100800001000011151185116020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3f51inst 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)cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000000050202160322003508780000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000000050202160232003507380000102003920039200392003920039
8002420038150000000006025800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000000050203160232003508880000102003920039200392003920039
8002420038150000000303925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000000050202160222003507380000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000000050202160222003508880000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000030050203160322003508880000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000001000050202160222003507380000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000000050202160222003507380000102003920039200392003920039
8002420038150000000006025800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000030050203160322003507380000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000000050203162222003507380000102019020039200392003920039