Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHL (vector, 4S)

Test 1: uops

Code:

  sqrshl v0.4s, v0.4s, v1.4s
  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)a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000030073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000000973116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043084230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000022073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshl v0.4s, v0.4s, v1.4s
  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)03090b1e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037211020110099100100100001000071011611296340100001003003830038300853008630038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225000229295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000371011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)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)9fa0a1a6a7a8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000005362954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954844100101010000101000050427731330018300373008228287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000116402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000007262954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830085
100243003722500000004412954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000007262954825100101010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000007262954825100171010000101000050427731330018300373003728287032876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrshl v0.4s, v1.4s, v0.4s
  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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000002823295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000002900071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011601296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183003730037282653287451010020010665200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000001693295211061011212810008112100005004277313300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313300183008430037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731310300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001002858640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216322963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731300300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrshl v0.4s, v8.4s, v9.4s
  sqrshl v1.4s, v8.4s, v9.4s
  sqrshl v2.4s, v8.4s, v9.4s
  sqrshl v3.4s, v8.4s, v9.4s
  sqrshl v4.4s, v8.4s, v9.4s
  sqrshl v5.4s, v8.4s, v9.4s
  sqrshl v6.4s, v8.4s, v9.4s
  sqrshl v7.4s, v8.4s, v9.4s
  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)031e1f3f51inst 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
80204200601550041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051102161120036800001002004020040200402004020040
8020420039150004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001001478051101161120036800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020091200491180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500061258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010003051101161120036800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040

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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481505114925800101080000108000050640000020059200392003999963100198001020800002016000020039200391180021109101080000100005020616532010080000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020316352003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020316362003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516532003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516662003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020516352003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020416352003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020316352003680000102004020040200402004020040
800242003915006125800941080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020616752003680000102004020040200402004020040
800242003915004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020316542003680000102004020040200402004020040