Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMULH (vector, 8H)

Test 1: uops

Code:

  sqrdmulh v0.8h, v0.8h, v1.8h
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037220822548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372302912548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230822548251000100010003983133018303730372415328951000100020003037303711100110001073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372203172548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrdmulh v0.8h, v0.8h, v1.8h
  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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722509329548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373022811102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043008522506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225012429548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373017911102011009910010010000100797101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250100000822954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006404163429630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006404164329630010000103003830038300383003830038
100243003722500000001242954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006403163429630010000103003830038300383003830038
100243003722500000001452954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006403164429630010000103003830038300383003830038
100243003722500000001662954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006404164429630010000103003830038300383003830038
100243003722500000008322954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006404164329630010000103003830038300383003830038
1002430037225000000011242954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006404164429630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006404164329630010000103003830038300383003830038
100243003722500000005832954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006404164429630010000103003830038300383003830038
100243003722400000001262954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000000006403164429630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrdmulh v0.8h, v1.8h, v0.8h
  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)0318191e1f3a3f4e51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000082295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000100071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037211020110099100100100001000000071011611296349100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000100071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282873287451010020010000200200003003730181111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038

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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224012829548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383008530038
1002430037225072629548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100306402162229630010000103003830038300383003830038
1002430037225186129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103008130038300383003830038
1002430037225072629548251001010100001010000504277313130018300373003728287328767100102010000202000030083300851110021109101010000100006402162229630010000103003830038300383003830038
1002430037225072629548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225216129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrdmulh v0.8h, v8.8h, v9.8h
  sqrdmulh v1.8h, v8.8h, v9.8h
  sqrdmulh v2.8h, v8.8h, v9.8h
  sqrdmulh v3.8h, v8.8h, v9.8h
  sqrdmulh v4.8h, v8.8h, v9.8h
  sqrdmulh v5.8h, v8.8h, v9.8h
  sqrdmulh v6.8h, v8.8h, v9.8h
  sqrdmulh v7.8h, v8.8h, v9.8h
  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)0307080a1e1f3a3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015110100248258010010080000100800005006400000200202003920039997339997801002008000020016020820143200391180201100991001008000010005114121610920036800001002004020040200402004020040
80204200391501110024825801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511491610920036800001002004020040200402004020040
8020420039150101002482580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051141016101020036800001002004020040200402004020040
8020420039150101002482580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051141016101020036800001002004020040200402004020040
80204200391501010024825801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511410169720036800001002004020040200402004020040
802042003915010100248258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010005114101611620036800001002004020040200402004020040
802042003915010100248258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010005114101691020036800001002004020040200402004020040
80204200391501010029025801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511411169920036800001002004020040200402004020040
80204200391501010024825801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000511410169920036800001002004020040200402004020040
8020420039150101002482580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051147169420036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa8cdcfd5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050203160002320036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050203160004320036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050202160003420036080000102004020040200402004020040
80024200391500014925800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050204160002220036080000102004020040200402009020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050203160002420036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050202160003220036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050203160002220036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050202160002220036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050202160003220036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016021420039200391180021109101080000100050203160004420036080000102004020040200402004020040