Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMULH (scalar, H)

Test 1: uops

Code:

  sqdmulh h0, h0, h1
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073316112630100030383038303830383038
1004303723914525482510001000100039831303018308430372415328951000100020003037303711100110001073116112630100030383038303830383038
1004303723061254825100010001149398313130183037303724153289510001000200030373037111001100051873116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110009073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110002073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372208425482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqdmulh h0, h0, h1
  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)030708090b18191e1f3f4e51inst 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)5e60696d6edispatch 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240000001508810329548251010010010000100100005004277313203001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071031611296340100001003003830038300383003830038
1020430037225001001006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000171011611296340100001003003830038300383003830038
10204300372250000000072629548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003008530038300383003830083
1020430037225000000006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010002000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
1020430037224000000006129548251010010010000100100005004277313003001830037300372826532874510100200100002002000030037300371110201100991001001000010000000060071011611296340100001003003830038300383003830038
1020430037232000000006129548251010010010000100100005004277313013001830037300372826532874510100200100002002000030037300371110201100991001001000010000000090071011611296340100001003003830038300383003830038

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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000006402169229630210000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103008530038300383003830038
100243003722500000006129548251001010100001010000504277313030018300853003728287328767100102010000202000030037300371110021109101010000100000000006402162229774010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313130018300373003728305328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000003016402162229668010000103003830038300853003830038

Test 3: Latency 1->3

Code:

  sqdmulh h0, h1, h0
  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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2c3c5branch mispredict (cb)cdcfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000022800728295482510100100100001001000050042773130030018300373003728272628741101002001000820020016300373003711102011009910010010000100000000001117170001600296460100001003003830038300383003830038
102043003722500000390061295482510100100100001001000050042773130030018300373003728272728741101002001000820020016300373003711102011009910010010000100000000001117180001600296470100001003003830038300383003830038
102043003722500000420076295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000007100011611296340100001003003830038300383003830038
102043003722500000750061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000100000007100011611296340100001003003830038300383003830038
10204300372250000060061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000007100011611296340100001003003830038300383003830038
102043003722500000150061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000007100011611296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000007100011611296340100001003003830038300383003830038
10204300372250000060061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000007100011611296340100001003003830038300383003830038
102043003722500000240061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000000007100011611296340100001003003830038300383003830038
1020430037224000001500612954825101001001000010010000500427731300300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000300130007100011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001006402162229630110000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001006402162229642010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020101622020000300373008411100211091010100001006402162229630010000103003830038300383003830038
100243003722400061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001006402162229630010000103003830038300383003830038
1002430037225000106295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020103242020000300373003711100211091010100001006402163229630010000103003830038300383003830038
100243003722400061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100221091010100001006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqdmulh h0, h8, h9
  sqdmulh h1, h8, h9
  sqdmulh h2, h8, h9
  sqdmulh h3, h8, h9
  sqdmulh h4, h8, h9
  sqdmulh h5, h8, h9
  sqdmulh h6, h8, h9
  sqdmulh h7, h8, h9
  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)696b6d6edispatch 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)9fa7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601501569258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511021611200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391501841258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511021611200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
8020420039151041258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500136258010010080000100800005006400002002002003920039997303999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
802042003915040241258010010080000100800005006400002002002003920039997303999780100200801442001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040

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)696b6d6edispatch 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)9fa1a6a8acc2branch mispredict (cb)cfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915042402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000000502001161120036080000102004020040200402004020040
8002420039150444402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000000502001161120036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000300502001161120036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000000502001161120036080000102004020040200402004020040
80024200391503304025800101080000108000050640000200200200392003999962610019800102080000201600002003920039118002110910108000010009000502001161120036080000102004020040200402004020040
80024200391500402580022108000010800005064000020020020039200399996310019800102080000201600002003920039418002110910108000010000000502001161120036180000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000000502001161120036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000000502001161120036080000102004020040200402004020040
800242003915033402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000000502001161120036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020020039200399996310019800102080000201600002003920039118002110910108000010000000502001161120036080000102004020040200402004020040