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, 4H)

Test 1: uops

Code:

  sqrdmulh v0.4h, v0.4h, v1.4h
  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
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000373116112630100030383038303830383038
100430372306125482510001000100039831303018303730372414328951000100020003037303711100110000073116112630100030383038303830383038
100430372336125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112627100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372296125482510001000100039831303018303730372415328951000100020003037303711100110000075116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116322627100030383038303830383038
1004303722028125482510001000100039831313018303730372415328951000100020003037303711100110000073116222630100030383038303830383038
1004303722126125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrdmulh v0.4h, v0.4h, v1.4h
  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)030818191e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100010071021611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100220071011611297060100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722400006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500006129548451010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000105100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100012071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225000126129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100010671011611296342100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b1e1f3f4e51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500006429548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250000942954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000105001640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372240001086129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722501006129548251001010100001010000504277313130018300373003728287032876710161201000020200003003730037111002110910101000010000000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrdmulh v0.4h, v1.4h, v0.4h
  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)033f4e51inst 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
10204300372256129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100071011611296340100001003003830038300383003830038
10204300372336129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100071011611296340100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100071011611296340100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100371011611296340100001003003830038300383003830038
102043003722561295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000710116112963421100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100071011611296340100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020348300373003711102011009910010010000100071011611296340100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100071011611296340100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100071011611296340100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030918191e1f3f4e51inst 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
100243003727800012072629548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000102106402162229630010000103003830038300383003830038
10024300372780001206129548251001010100001010000504277313030018300373003728287328767100102010000202032630037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037260000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037260000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037260000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383022730038
1002430037241000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162329630010000103003830038300383003830038
1002430037241000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100036402162229630010000103003830038300383003830038
1002430037241040006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037241000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037233000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrdmulh v0.4h, v8.4h, v9.4h
  sqrdmulh v1.4h, v8.4h, v9.4h
  sqrdmulh v2.4h, v8.4h, v9.4h
  sqrdmulh v3.4h, v8.4h, v9.4h
  sqrdmulh v4.4h, v8.4h, v9.4h
  sqrdmulh v5.4h, v8.4h, v9.4h
  sqrdmulh v6.4h, v8.4h, v9.4h
  sqrdmulh v7.4h, v8.4h, v9.4h
  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)030b1e1f3f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915000010425801001008000010080000500640000120083201002003999733999780100200800002001601962010420100218020110099100100800001000005110416112007613800001002004020040201012004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
80204200391500005162580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100130511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
80204200391500001042580100108800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100130511011611200360800001002004020040200402004020040
8020420039150000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)5f60696b6d6edispatch 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)9fa1a8acc2c5cfd2d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000402580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100000050200121610102003689180000102004020040200402004020040
80024200391500000402580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100100150200121613112003674080000102004020040200402004020040
80024200391500000402580010108000010800005064000000200200200392003999963100198001020800002016000020039200391180021109101080000100000050200131611132003673080000102004020040200402004020040
8002420039150000040258001010800001080000506400000020020020039200399996310019800102080000201600002003920039118002110910108000010001740050200121611122003672080000102004020040200402004020040
80024200391500000402580010108000010800005064000001200203200392003999963100198001020800002016000020039200391180021109101080000100030050200121612112003691880000102004020040200402004020040
80024200391500000402580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100000050200121611112003687080000102004020040200402004020040
800242003915000004025800101180000108000050640000012002002003920039999631001980010208000020160000200392003911800211091010800001000000502007167142003673080000102004020040200402004020040
8002420039150000040258001010800001080000506400000020020020039200399996310019800102080000201600002003920039118002110910108000010000005020011168122003672080000102004020040200402004020040
800242003915000003252580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100200050200121612122003673080000102004020040200402004020040
80024200391500000402580010108000010800005064000001200200200392003999963100198001020800002016000020039200391180021109101080000100000050200121611122003687080000102004020040200402004020040