Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULL2 (by element, 2D)

Test 1: uops

Code:

  sqdmull2 v0.2d, v0.4s, 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)03080b18191e1f3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073216112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303722000090612548251000100010003983131301830373037241532895100010002000303730371110011000000003073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303722000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmull2 v0.2d, v0.4s, 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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313030018300373003728272628741101002001000820020016300373003711102011009910010010000100001117170160029647100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010006440007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037224025129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225025129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100200007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005774277313130018300843003728265328745101002001000020020000300373003721102011009910010010000100100007351253129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080b18191e1f3f4e51inst 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)9fa0a1acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqdmull2 v0.2d, v1.4s, 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)031e3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225001472954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500822954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225001722954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611297040100001003003830038300383003830038
102043003722500822954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250011742954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225005782954825101001001000010010000500427867513001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225001472954825101001001000710010000500427773513001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000014771012511296340100001003003830038300383003830038
102043003722500822954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225001072954825101001001000010010000500427731313001830037300372826532874510426200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000001032954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000001472954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830321
100243003722500000001492954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000005662954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500001800842954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000004732954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000001452954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000001452954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722400000002862954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmull2 v0.2d, v8.4s, v9.s[1]
  sqdmull2 v1.2d, v8.4s, v9.s[1]
  sqdmull2 v2.2d, v8.4s, v9.s[1]
  sqdmull2 v3.2d, v8.4s, v9.s[1]
  sqdmull2 v4.2d, v8.4s, v9.s[1]
  sqdmull2 v5.2d, v8.4s, v9.s[1]
  sqdmull2 v6.2d, v8.4s, v9.s[1]
  sqdmull2 v7.2d, v8.4s, 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)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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915000412580100100800001008000050064000002002020039200909982399978010020080000200160000200392003911802011009910010080000100000511021611200360800001002010320040200402004020040
802042003915000412580100100800001008000051064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150002302580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000832580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150001712580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150001042580100100800001008000053564000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039155901272580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391501072580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000050201516332003680000102004020040200402004020040
8002420039150105258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020316372003680000102004020040200402004020040
800242003915063258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020716332003680000102004020040200402004020088
800242003915082258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020716732003680000102004020040200402004020040
8002420039150124258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020316732003680000102004020040200402004020040
8002420039150944258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020316332003680000102004020040200402004020040
80024200391501049258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020316732003680000102004020040200402004020040
8002420039150943258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020316332003680000102004020040200402004020040
8002420039150325258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020716332003680000102004020040200402004020040
800242003915061258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020316732003680000102004020040200402004020040