Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHLU (vector, 2D)

Test 1: uops

Code:

  sqshlu v0.2d, v0.2d, #3
  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)030b181e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371600061168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020842037111001100001073216221786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000673216221786100020382038203820382038
100420371600061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
100420371500061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715001261168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshlu v0.2d, v0.2d, #3
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3a3f4e51inst 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)77~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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000006119686251010010010000100100006262847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071021631197910100001002003820038200382003820038
102042003715000000012619686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071021611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371490000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071021611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521020018200372003718421318745010100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000000821968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000007261968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006403162219786010000102003820038200382003820038
100242003715000000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000004411968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000001241968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshlu v0.2d, v8.2d, #3
  sqshlu v1.2d, v8.2d, #3
  sqshlu v2.2d, v8.2d, #3
  sqshlu v3.2d, v8.2d, #3
  sqshlu v4.2d, v8.2d, #3
  sqshlu v5.2d, v8.2d, #3
  sqshlu v6.2d, v8.2d, #3
  sqshlu v7.2d, v8.2d, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030408090a0b18191e1f3a3f51inst 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)9fa1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591501000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000007972580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000002700292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000001152580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
80204200381500000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039

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)9fa6a8accfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015008125800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050203316322003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050200316342003580000102003920039200392003920039
8002420038150010225800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200416322003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050200216322003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201216322003580000102003920039200392003920039
800242003815008125800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201316332003580000102003920039200392003920039
80024200381501203925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050201316232003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050201316332003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201316342003580000102003920039200392003920039
8002420038150010225800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050201316332003580000102003920039200392003920039