Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLP (vector, 8H)

Test 1: uops

Code:

  uaddlp v0.8h, v0.16b
  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)03081e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000373116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150961168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddlp v0.8h, v0.16b
  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)03181e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500001044196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007102161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000137101161119791100001002003820038200382003820038
1020420037150000862196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720084111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000281196862510116100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500001017196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010001207101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100010906403163319786010000102003820038200382003820038
100242003715000003012419686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
1002420037150000000272196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000107206403163319786210000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
100242003715000000012419686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006403173319786010000102003820038200382003820038
100242003715000000063119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uaddlp v0.8h, v8.16b
  uaddlp v1.8h, v8.16b
  uaddlp v2.8h, v8.16b
  uaddlp v3.8h, v8.16b
  uaddlp v4.8h, v8.16b
  uaddlp v5.8h, v8.16b
  uaddlp v6.8h, v8.16b
  uaddlp v7.8h, v8.16b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)033f51inst 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)9fa7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150322258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100030011151180160020035800001002003920039200392003920039
802042003815029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815071258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100200011151180160020035800001002003920039200392003920112
802042003815029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815094258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
8020420038149292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000460011151180160020035800001002003920039200392003920039
8020420038150641258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039
802042003815052258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a1e1f3f51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020416422003580000102003920039200392003920039
80024200381501006225800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001001005020216242003580000102003920039200392003920039
800242003815000010425800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020216242003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020416442003580000102003920039200392003920039
800242003815000061825800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020316422003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001001005020216422003580000102003920039200392003920039
800242003815000050925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020216442003580000102003920039200392003920039
80024200381500189012725800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000005020416432003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001002005020216242003580000102003920039200392003920039
800242003815000053925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000005020416422003580000102003920039200392003920039