Apple M1 Microarchitecture Research by Dougall Johnson

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

UQADD (vector, 16B)

Test 1: uops

Code:

  uqadd v0.16b, v0.16b, v1.16b
  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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a1acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372396125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430852206125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372296125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372308225482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd v0.16b, v0.16b, v1.16b
  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)030818191e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500001032954864101001001000810010000573427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250100612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3f4e51inst 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)9fa6a7a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250001712954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250007262954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250007262954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250007262954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000300640216222963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773131300183003730037282873287671001020100002020000300843003711100211091010100001000023400640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd v0.16b, v1.16b, 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): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100227207101161129634100001003003830230300383003830038
10204300372253608229548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010044307101161229665100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010053007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010040007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010043007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010043007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001005011707101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010055607101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010053007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100421207101161129634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773130300183003730037282870328767100102010000202000030037300371110021109101010000100120640316222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001200640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001590640116222963010000103003830038300383003830038
1002430037225062329548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010100640216222963010000103003830038300383003830038
1002430037225023229548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010090640216222963010000103003830038300383003830038
10024300372250822954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001740640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001440640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001710640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100960640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd v0.16b, v8.16b, v9.16b
  uqadd v1.16b, v8.16b, v9.16b
  uqadd v2.16b, v8.16b, v9.16b
  uqadd v3.16b, v8.16b, v9.16b
  uqadd v4.16b, v8.16b, v9.16b
  uqadd v5.16b, v8.16b, v9.16b
  uqadd v6.16b, v8.16b, v9.16b
  uqadd v7.16b, v8.16b, v9.16b
  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)03080b1e3f51inst 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
80204200581500106225801001008000010080000500640000120020200392003999736999780100200800002001600002003920039118020110099100100800001001051102161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000041448031810080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010025051101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001001051101161120036800001002004020040200402004020040
8020420039150000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100301251101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010029051101161120036800001002004020040200402004020040
802042003915000092325801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e3f51inst 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)9fa6a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100200050201161120036080000102004020040200402004020040
8002420039150004540258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000210050201161120036080000102004020040200402004020040
8002420039150000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010019180050201161120036080000102004020114200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001004200050201161120036080000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100160050201161120036080000102004020040200402004020040
80024200391500004025800101080099108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100030050201161120036080000102019920095200402004020040
8002420039150008044025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100030050201161120036080000102004020040200402004020040
800242003915000278225800101080000108000050640812120020200392003999963100198001020800002016000020039200391180021109101080000100060050201161120036080000102009120040200402004020040
8002420039150000409881084128107111810506064575212010220351203951009841100198085620811522016000020039200391180021109101080000100100050201161120036080000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100200050201161120036080000102004020040200402004020040