Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMULH (by element, H)

Test 1: uops

Code:

  sqrdmulh h0, h0, v1.h[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)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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100000673116112630100030383038303830383038
1004303722361254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723961254825100010001000398313130183037303724153289510001000200030373037111001100010073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000223973116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrdmulh h0, h0, v1.h[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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722504202954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010001067101161129634100001003003830038300383003830038
102043003722592292954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722401032954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250842954825101001001000010010000500427731313001830037300372826532874510100200100002002034830037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722503182954825101001001000010010000500427731313001830037300842826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722501242954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007105732129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722501202954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722502772954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722501452954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000010006402162229630010000103003830038300383003830038
100243003722500000015629548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000010006402162229630010000103003830038300383003830038
1002430037225000000251295482510010151000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000430906402162229630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000010006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000010006402162229630010000103003830038300383003830038
100243003722500000028629548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000000306402162229630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000020006402162229630010000103003830038300383003830038
10024300372250000007262954810310010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100000320306402162229630010000103003830038300383003830038
100243003722500000044129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000010006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrdmulh h0, h1, v0.h[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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037235082295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011621296340100001003003830038300383003830038
10204300372250497295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100221071011611296340100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250538295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003721102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011621296340100001003003830038300383003830038
10204300372250166295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250103295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250106295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000071011621296340100001003003830038300383003830038

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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250001032954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010100640616222963010000103003830038300383003830038
10024300372250001262954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010100640216222963010000103003830038300383003830038
1002430037225000842954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222970110000103003830038300383003830038
1002430037225000842954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250001892954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500020512954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250002982954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000842954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000842954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000842954825100101010000101000050427731303001830037300372828732876710010201018020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrdmulh h0, h8, v9.h[1]
  sqrdmulh h1, h8, v9.h[1]
  sqrdmulh h2, h8, v9.h[1]
  sqrdmulh h3, h8, v9.h[1]
  sqrdmulh h4, h8, v9.h[1]
  sqrdmulh h5, h8, v9.h[1]
  sqrdmulh h6, h8, v9.h[1]
  sqrdmulh h7, h8, v9.h[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)0307080a0b18191e1f3a3f51inst 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
8020420039150000000000104258010010080000100800005006400001200202003920039998903999780100200800002001600002003920039118020110099100100800001000000000511031633200360800001002004020040200902004020040
80204200391500000000004125801001008000010080000500640000120020200392003999737310024801002008000020016000020039200391180201100991001008000010000000120511021622200360800001002004020040200402004020040
802042003915000000000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000060511021622200360800001002004020040200402004020040
8020420039150000000600150258010010080000100800005006400001200202003920039997303999780100200801042001600002003920039118020110099100100800001000000000511021622200360800001002004020040200402004020040
802042003915000000000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000000511021622200360800001002004020040200402004020040
802042003915000000000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000000511021622200360800001002004020040200402004020040
802042003915000000000041258010010080000100800005006400001200202003920039997303999780100200800002001600002003920091118020110099100100800001000000000511021622200360800001002004020040200402004020040
802042003915000000000041258010010080000100800005006400000200202003920039997303999780100200800002001600002003920039118020110099100100800001000000000511021622200360800001002004020040200402004020040
8020420039150000000000146258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000000511021622200360800001002004020040200402004020040
80204200391500000000001867258010010080000100800005006400001200202003920039997303999780100200800002001600002003920039118020110099100100800001000000000511021622200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6dadbddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000000050206168022200360080000102004020040200402004020040
800242003914900000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050202168022200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392009099963100198001020800002016000020039200391180021109101080000100000000050202167022200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050202167122200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050202167022200360080000102004020040200402004020040
80024200391500000000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000040948050542167022200360080000102004020040200402004020040
8002420039150000012004043801101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000000050202165022200360580000102004020040200402004020040
800242003914900000004025800101080000128000050640000020020200902003999963100198001020800002016021220040200982180021109101080000100000000050203165022200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050206164022200360080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000000050206164022200360080000102004020040200402004020040