Apple M1 Microarchitecture Research by Dougall Johnson

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

MOVI (vector, 4H, lsl)

Test 1: uops

Code:

  movi v0.4h, #3, lsl #8

(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)031e3f51inst 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)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882045251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
10042882040251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289

Test 2: throughput

Count: 8

Code:

  movi v0.4h, #3, lsl #8
  movi v1.4h, #3, lsl #8
  movi v2.4h, #3, lsl #8
  movi v3.4h, #3, lsl #8
  movi v4.4h, #3, lsl #8
  movi v5.4h, #3, lsl #8
  movi v6.4h, #3, lsl #8
  movi v7.4h, #3, lsl #8

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03080b0f18191e1f3a3f51inst 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)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)9fa0a1a6a8a9aaacc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815500000000149258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000030511021622200350800001002003920039200392003920039
80204200381550000000040258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000020000511021622200350800001002003920039200392003920039
802042003815600000000230258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815500000000635258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815600000120063258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815500000000302258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815500000000759258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
802042003815500000000235258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
80204200381560000000040258010010080000100800005005600000200192003820038997339996801002008009720020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039
80204200381560040000082258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010000000000511021622200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b181e1f3a3f51inst 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)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
800242004715511000014725800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050222163320035080000102003920039200392003920039
8002420038155110000181325800101080000108000050560000020019200382003899963100188001020800002020038200381180021109101080000100050223162320035080000102003920039200392003920039
8002420038155110000191525800101080000108000050560000020019200382003899963100188001020800002020038200381180021109101080000100050223163320035080000102003920039200392003920039
8002420038155110000193925800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050223163320035080000102003920039200392003920039
8002420038155110000193425800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050223163220035080000102003920039200392003920039
8002420038155110000192025800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050222163320035080000102003920039200392003920039
800242003815511000014725800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050222163320035080000102003920039200392003920039
800242003815511000014725800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050223163320035080000102003920039200392003920039
8002420038156110000115425800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050223163320035080000102003920039200392003920039
800242003815511000014525800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100050223163320035080000102003920039200392003920039