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, 2S, lsl)

Test 1: uops

Code:

  movi v0.2s, #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)031e1f3f51inst 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
100428820040251000100010007000126928828812331461000100028828811100110000073316222851000289289289289289
100428820040251000100010007000026928828812331461000100028828811100110000073216222851000289289289289289
100428820040251000100010007000026928828812331461000100028828811100110000073216222851000289289289289289
100428820040251000100010007000126928828812331461000100028828811100110000073216222851000289289289289289
100428820040251000100010007000126928828812331461000100028828811100110001073216222851000289289289289289
100428820040251000100010007000026928828812331461000100028828811100110000073216222851000289289289289289
100428820040251000100010007000126928828812331461000100028828811100110000073216222851000289289289289289
1004288212040251000100010007000126928828812331461000100028828811100110000073216222851000289289289289289
100428820040251000100010007000126928828812331461000100028828811100110000073216222851000289289289289289
100428820040251000100010007000126928828812331461000100028828811100110000073216222851000289289289289289

Test 2: throughput

Count: 8

Code:

  movi v0.2s, #3, lsl #8
  movi v1.2s, #3, lsl #8
  movi v2.2s, #3, lsl #8
  movi v3.2s, #3, lsl #8
  movi v4.2s, #3, lsl #8
  movi v5.2s, #3, lsl #8
  movi v6.2s, #3, lsl #8
  movi v7.2s, #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)03090a181e3f51inst 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)5e60696d6edispatch 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)9fa8acc2c5cdcfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591550000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511051622200350800001002003920039200392003920039
80204200381550000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
8020420038155000010912580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200351800001002003920039200392003920039
80204200381560000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
80204200381560000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
80204200381550000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
80204200381560000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
80204200381550000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
80204200381550000932580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
80204200381550000402580100100800001008000050056000000200192003820038997339996801002008000020020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080918191e1f3f51inst 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)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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048155000000039258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100050200057166520035080000102003920039200392003920039
8002420038155000000039258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100050200057167720035080000102003920039200392003920039
8002420038156000000039258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100050200056166720035080000102003920039200392003920039
8002420038156000000083258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100050200067165720035080000102003920039200392003920039
8002420038155000000039258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100350200065166620035080000102003920039200392003920039
80024200381560000000392580010108000010800005056000012001902003820038999631001880010208000020200382003811800211091010800001009050200056166520035080000102003920039200392003920039
8002420038155000000039258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100050200056166520035080000102003920039200392003920039
8002420038155000000039258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100050200056167520035080000102003920039200392003920039
80024200381550000000392580010108000010800005056000012001902003820038100043100188001020800002020038200381180021109101080000100050200067165620035080000102003920039200392003920039
8002420038155000000039258001010800001080000505600001200190200382003899963100188001020800002020038200381180021109101080000100050200067168720035080000102003920039200392003920039