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, 4S)

Test 1: uops

Code:

  sqshlu v0.4s, v0.4s, #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)03191e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000001873116111786100020382038203820382038
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000014873116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038208620852038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
1004203715018156168625100010001000264521020182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100021073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000673116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshlu v0.4s, v0.4s, #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)031e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150126119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003721102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100121010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671022820100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000066119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402164219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000106402162219786010000102003820038200382003820038
100242003715000008219686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382013420038

Test 3: throughput

Count: 8

Code:

  sqshlu v0.4s, v8.4s, #3
  sqshlu v1.4s, v8.4s, #3
  sqshlu v2.4s, v8.4s, #3
  sqshlu v3.4s, v8.4s, #3
  sqshlu v4.4s, v8.4s, #3
  sqshlu v5.4s, v8.4s, #3
  sqshlu v6.4s, v8.4s, #3
  sqshlu v7.4s, v8.4s, #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)0304080918191e1f3f51inst 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)9fa1a6a7a8a9acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611501000090117258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511821620035800001002003920039200392003920039
8020420038150000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511811620035800001002003920039200392003920039
8020420038150000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039
8020420038150000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039
8020420038150000009029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039
8020420038150000000073258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039
80204200381500000000287258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039
8020420038150000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039
8020420038150000000029258010810080008112800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039
8020420038150000000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000000111511801620035800001002003920039200392003920039

1000 unrolls and 10 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500109258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010002050201516151220035080000102003920039200392003920039
8002420038150098258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201616121620035080000102003920039200392003920039
8002420038150067258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201516141620035080000102003920039200392003920039
8002420038150067258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201316131020035080000102003920039200392003920039
8002420038150067258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201516141420035080000102003920039200392003920039
8002420038150067258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201016161320035080000102003920039200392003920039
800242003815007925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000015950201216141420035080000102003920039200392003920039
8002420038150067258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201616121620035080000102003920039200392003920039
8002420038150067258001010800001080108506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201316121520035080000102003920039200392003920039
8002420038150067258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000050201716161420035080000102003920039200392003920039