Apple M1 Microarchitecture Research by Dougall Johnson

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

SQADD (scalar, H)

Test 1: uops

Code:

  sqadd 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)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
100430372324612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110004073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372303352548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830853038
10043037270612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372336125482510001000100039831330183037303724153289510001000200030373037111001100032073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqadd 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)030b1e3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722509612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300841110201100991001001000010000000027101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250033252954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830081300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830133300852827832874510563200100002002066230037300371110201100991001001000010027300549507101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038

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)696d6edispatch 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
100243003722406129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722406129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000036402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqadd 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)030b18191e3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129706100001003003830038300383003830038
1020430037225000061295488610100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250003961295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000001007101161129634100001003003830038300383003830038
10204300372250000768295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e1f3f4e51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225024061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500061295482510010101000013101495042773130300183003730037282873287671001020100002020000300373003711100211091010100001000030640216222963010000103003830038300383003830038
1002430037225020101501295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225018061295482510010101000010100005042773130300183003730037282873287671001020100002020984300373003711100211091010100001001200640216222963010000103003830229300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225012061295482510010141000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500082295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250159061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640233222963010000103003830038301793003830038
100243003722500061295482510010101000012100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001003060640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqadd h0, h8, h9
  sqadd h1, h8, h9
  sqadd h2, h8, h9
  sqadd h3, h8, h9
  sqadd h4, h8, h9
  sqadd h5, h8, h9
  sqadd h6, h8, h9
  sqadd 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)030b1e3f51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511021611200360800001002004020040200402004020040
802042003915000852580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000852580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150001652580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150048412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100119030512711611200360800001002004020040200402004020040
8020420039150003892580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100100511011611200360800001002004020040200402004020040
8020420039150001672580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e1f3f5051inst 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)9fa0a8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000174025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020051624200360080000102004020040200402004020040
80024200391490000402002325800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020041642200360080000102004020040200402004020040
80024200391500000379025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020021624200360080000102004020040200402004020040
8002420039150000040025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020021624200360080000102004020040200402004020040
80024200391500000429025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020041642200360580000102004020040200402004020040
8002420039150000040025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020021642200360080000102004020040200402004020040
8002420039150000082025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020021624200360080000102004020040200402004020040
8002420039150000040025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020041624200360080000102004020040200402004020040
80024200391500000103025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020041642200360080000102004020040200402004020040
8002420039150000040025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020421634200360080000102004020040200402004020040