Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULL (by element, 2D)

Test 1: uops

Code:

  sqdmull v0.2d, v0.2s, v1.s[1]
  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)033f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372261254825100010001000398313130183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000200030373037111001100001073416222630100030383038303830383038
100430372382254825100010001000398313030183037303724153289510001000200030373037111001100000073416222630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
1004303723170254825100010001000398313130183037303724153289510001000200030373037111001100000073316222630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmull v0.2d, v0.2s, v1.s[1]
  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)03083f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007331161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722509432954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250892954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002142000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006404162229630010000103003830038300383003830038
10024300372240000002512954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229668010000103003830038300383003830038
10024300372250000002512954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000016403162229630010000103003830038300383003830038
10024300372250000005992954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
10024300372250000004412954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
1002430037224000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000015006404162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqdmull v0.2d, v1.2s, v0.s[1]
  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)6061696d6edispatch 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)9fa0a8acc2branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722518612954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731300300183003730037282733287451010020210000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
102043003722401562954825101001001000010010000500427731300300183003730037282653287451010020010000200213043003730037111020110099100100100001000100071051161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
102043003722507262954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
102043003722507262954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071051161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731300300183008530037282653287451010020410000200200003003730089411020110099100100100001000200071051161129634100001003003830038300383003830038

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)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
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640416432963010000103003830038300383003830038
10025300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037211002110910101000010001640416442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020209843003730037111002110910101000010000640316442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640416442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640416442963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010090640216342963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640416442963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003008530037111002110910101000010000640316442966410000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216342963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmull v0.2d, v8.2s, v9.s[1]
  sqdmull v1.2d, v8.2s, v9.s[1]
  sqdmull v2.2d, v8.2s, v9.s[1]
  sqdmull v3.2d, v8.2s, v9.s[1]
  sqdmull v4.2d, v8.2s, v9.s[1]
  sqdmull v5.2d, v8.2s, v9.s[1]
  sqdmull v6.2d, v8.2s, v9.s[1]
  sqdmull v7.2d, v8.2s, v9.s[1]
  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)03041e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511041623200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511021623200360800001002004020040200402004020040
8020420039150012412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180202100991001008000010000511021623200361800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511031623200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511031615200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511031633200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000511031623200360800001002004020040200402004020040

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80025200481500402580010108000010800005064000002002020039200399996310019800102080000201600002003920190118002110910108000010005020316112003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200899996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
800242003915051402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500402880010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
8002420039150183402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005020116112003680000102004020040200402004020040