Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULL2 (vector, 2D)

Test 1: uops

Code:

  sqdmull2 v0.2d, v0.4s, v1.4s
  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)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)acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372266125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100036073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372308225482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmull2 v0.2d, v0.4s, v1.4s
  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)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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000061295482510100100100001001000050042773131300183003730037282653288161010020010000200200003003730037111020110099100100100001000002000071011611296340100001003008730038300383003830038
10204300372240000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000037000071011611296340100001003003830038300383003830038
10204301322250000000105295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000001030071011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042786701300183003730037282653287451010020010000200200003003730037111020110099100100100001000007030071011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282683287451010020010000200200003003730037111020110099100100100001000200030071011611296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000030071011611296340100001003003830038300383003830038
10204300372250000000631295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000030071011611296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001000050042773131300183003730037282653287451010020010000204200003003730037111020110099100100100001002000030071011611296340100001003003830038300383003830038
10204300372240000000189295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000030071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722510000006129548251001212100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
100243003722500000006129548251001012100001210000604277313130018300373003728287328767100102010000202000030037300371110021109101010000100000100006424164429632010000103003830038300383003830038
100243003722500000006229548251001212100081010000604277313130018300373003728287328767100122010000202000030037300371110021109101010000100000100006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000009006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000005403006402162229630010000103003830038300383003830038
1002430037224100000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000002806006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000012100005042773131300183003730037282873287671001220100002020000300373003711100211091010100001000005400006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001210000604277313130018300373003728287328767100102010000202000030037300371110021109101010000100000003006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000604277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037311002110910101000010000000102006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqdmull2 v0.2d, v1.4s, v0.4s
  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)0308191e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001002137101161129634100001003003830038300383003830038
102043003722510061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000137101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000507101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282873287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000237101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)9fa6a8a9acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722502622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010010000644101610102963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000064410161052963010000103003830038300383003830038
100243003722402942954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000644121612102963010000103003830038300383003830038
100243003722402622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010026030064412165102963010000103003830038300383003830038
100243003722502622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010034000644101610102963010000103008530085300383003830038
100243003722502622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010020000644101612122963010000103003830038300383003830038
100243003722502622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000644816882963010000103003830038300383003830038
1002430037224122622954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000644121612122963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000064410161052963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001004030064410165122963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmull2 v0.2d, v8.4s, v9.4s
  sqdmull2 v1.2d, v8.4s, v9.4s
  sqdmull2 v2.2d, v8.4s, v9.4s
  sqdmull2 v3.2d, v8.4s, v9.4s
  sqdmull2 v4.2d, v8.4s, v9.4s
  sqdmull2 v5.2d, v8.4s, v9.4s
  sqdmull2 v6.2d, v8.4s, v9.4s
  sqdmull2 v7.2d, v8.4s, v9.4s
  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)60696b6d6edispatch 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391509412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010000051102162120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002002003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002002003920039997339997801002008000020016027220039200391180201100991001008000010001351101161120036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000239951101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002002003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa6a7a8a9acc2cfd0d2d5d6ddinst fetch restart (de)dfe0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000050243041653320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000103050243031634320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000400050243031633320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000050243051655320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000050243041633320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000050243031643320036080000102004020040200402004020040
8002420039150000000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010004401890050243051633320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000100050243051623320036080000102004020040200402004020040
8002420039150000000515258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000100050243031643320036080000102004020040200402004020040
800242003915000000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000050243031633320036080000102004020040200402004020040