Apple M1 Microarchitecture Research by Dougall Johnson

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

UQADD (scalar, D)

Test 1: uops

Code:

  uqadd d0, d0, d1
  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)031e1f3f4e51inst 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
1004303722006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
10043037220061254825100010001000398313030183037303724153289510001000200030373037111001100002773116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037221206125482510001000100039831303018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
100430372212886125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd d0, d0, d1
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722501397295482510100100100001001000050042773130300183003730037282653287451010020010000202203223003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250189295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250166295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722501070295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722501043295482510100100100001141000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722501170295482510100100100001001000050042773130300183003730037282653287451025620010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250981295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250934295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722501060295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240922295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa0a6a7a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006404165529630010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006404165529630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006406166629630010000103003830038300383003830038
100243003722500009006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006405165629630010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100001000006405166529630010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006406166629630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000001440006405165529630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006405164629630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006406166529630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030054300373003728287328767100102010000202000030037300371110021109101010000100000000006405164629630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd d0, d1, d0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3a3f4e51inst 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)9fa0a1a8a9acc5branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500047129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
10204300372250018229548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373008411102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722500084829548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722500018929548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722500014529548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722500014529548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722500014529548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722400071629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722500021629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038
102043003722500014929548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071001161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000103529548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000306402163229668210000103003830038300383003830038
1002430037225101000082129548251001010100001010000504277313130018300373003728287328767100102010167202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000012095129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000080329548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000306402162229630010000103003830038300383003830038
100243003722500000408023129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000030029548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250000000271829548251001010100001010000504277313130018300373003728287328767101602010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000014729548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000016629548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000025429548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000102205560046843324229702110000103008630130300853008430086

Test 4: throughput

Count: 8

Code:

  uqadd d0, d8, d9
  uqadd d1, d8, d9
  uqadd d2, d8, d9
  uqadd d3, d8, d9
  uqadd d4, d8, d9
  uqadd d5, d8, d9
  uqadd d6, d8, d9
  uqadd d7, d8, d9
  movi v8.16b, 9
  movi v9.16b, 10

(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)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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059151037325801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511061611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915004125801001008008410080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001001511011611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511021611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
8020420039150010425801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915006425801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040
8020420039150061325801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)5f60696d6edispatch 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)9fa8accfd0d5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150024025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010005020011600112003680000102004020040200402004020040
8002420039150904025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010065020011600112003680000102004020040200402004020040
80024200391500070525800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010005020011600112003680000102004020040200402004020040
8002420039150004025800101080000148000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010005020011600112003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010005020011600112003680000102004020040200402004020040
80024200391500063258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000102935020011611112003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010005020011600112003680000102004020040200402004020040
80024200391500058025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010005020411600112003680000102004020040200402004020040
80024200391500075125800221080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010005020011600112003680000102004020040200402004020040
8002420039150006325800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010005020011600112003680000102004020040200402004020040