Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHLL (2D)

Test 1: uops

Code:

  sshll v0.2d, v0.2s, #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)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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371512611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150821686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000173116111786100020382038203820382038
100420371621611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshll v0.2d, v0.2s, #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)0308090b1e3f4e51inst 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
102042003715000006119686251010010010000100101525002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010410012100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100067101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000053619686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000061196866410100100100001001000050028475210200182003720037184213187451010020410000200100002003720037111020110099100100100001003007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001002537101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318765101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000001206119686251001010100001010000822847521120018200372003718443318767100102010000201000020037200371110021109101010000100000003006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000709006402162219786010000102003820038200382003820038
100242003715000001206119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000003006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006006402162219786010000102003820038200382003820038
1002420037151000021061196861021002310100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000200006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
10024200371490000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402165219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshll v0.2d, v8.2s, #3
  sshll v1.2d, v8.2s, #3
  sshll v2.2d, v8.2s, #3
  sshll v3.2d, v8.2s, #3
  sshll v4.2d, v8.2s, #3
  sshll v5.2d, v8.2s, #3
  sshll v6.2d, v8.2s, #3
  sshll v7.2d, v8.2s, #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)03081e3f51inst 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)9fa6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000011151180160020035800001002009220039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000476211151180160020035800001002009120039200952003920039
802042003815100712580108100800081008002050064013220019200382003899776998980120200801342008003220038200383180201100991001008000010000020011151180160020035800001002003920039200392003920039
802042003815013502580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000100011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000011151180160020035800001002003920039200392003920039
8020420038150007125801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100200015011151180160020035800001002015420039200392003920049
8020420038151027712580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000011151180160020035800001002003920039200392003920039
802042003815000298280108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000100011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000010050208163520035080000102003920039200392003920039
800242003815000000392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010000520350204165320035080000102003920039200392003920039
8002420038150000504039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000010350204164620035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050203165320035080000102003920039200392003920039
800242003815000000704258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050203164520035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050204163620035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050206163520035080000102003920039200392003920039
80024200381500000039258001010803741080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000010350455165320035080000102003920039200392003920039
8002420038150000001022580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010000007550205165320035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050203163520035080000102003920039200392003920039