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, 8H, lsl)

Test 1: uops

Code:

  movi v0.8h, #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
10042882040251000100010007000126928828812331461000100028828811100110000073416332851000289289289289289
10042882040251000100010007000126928828812331461000100028828811100110000073316332851000289289289289289
10042882040251000100010007000126928828812331461000100028828811100110000073316332851000289289289289289
10042882040251000100010007000126928828812331461000100028828811100110000073316322851000289289289289289
10042882040251000100010007000126928828812331461000100028828811100110000073316332851000289289289289289
10042882040251000100010007000126928828812331461000100028828811100110000073316322851000289289289289289
10042883040251000100010007000126928828812331461000100028828811100110000073316332851000289289289289289
10042882040251000100010007000126928828812331461000100028828811100110000073316332851000289289289289289
10042883040251000100010007000126928828812331461000100028828811100110000073316322851000289289289289289
10042882040251000100010007000126928828812331461000100028828811100110000073316332851000289289289289289

Test 2: throughput

Count: 8

Code:

  movi v0.8h, #3, lsl #8
  movi v1.8h, #3, lsl #8
  movi v2.8h, #3, lsl #8
  movi v3.8h, #3, lsl #8
  movi v4.8h, #3, lsl #8
  movi v5.8h, #3, lsl #8
  movi v6.8h, #3, lsl #8
  movi v7.8h, #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)03080b18191e1f3f51inst 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)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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060156000000402580100100800001008000050056000020019200382003899733999680100200800002002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038155000000402580100100800001008000050056000020019200382003899733999680100200800002002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038155000000402580100100800001008000050056000020019200382003899733999680100200800002002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038155000000402580100100800001008000050056000020019200382003899733999680100200800002002003820038118020110099100100800001000000000111511811600200350800001002003920039200392003920039
8020420038155000000292580108100800081008002050056012820019200382003899776998980120200800322002003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038155000000292580108100800081008002050056012820019200382003899776998980120200800322002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038155000000402580100100800001008000050056000020019200382003899733999680100200800002002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
80204200381560000264884025801001138009211380192500560000200192009020038998313999680100200801952002014120090118020110099100100800001000000000000511022722200350800001002003920039200392003920141
8020420038156100000402580100100800001008000050056000020019200382003899733999680406200800002002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
802042003815500431320402580100100800001008000050056000020019200382003899733999680100200800002002009320144118020110099100100800001000000000000511031622200760800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa8accficache miss (d3)d5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155000392580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010005020021600812003580000102003920039200392003920039
8002420038155000392580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010005020011600512003580000102003920039200392003920039
8002420038155000392580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010005020011600312003580000102003920039200392003920039
8002420038155000392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010005020011600612003580000102003920039200392003920039
8002420038155000392580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010005020011600512003580000102003920039200392003920039
80024200381560003925800101080000108000050560000020019200382003899963100188001020800002020038200381180021109101080000101050200116001012003580000102003920039200392003920039
8002420038155000392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010065020011600112003580000102003920039200392003920039
8002420038155000392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010005020011600112003580000102003920039200392003920039
8002420038155000392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010105020011600112003580000102003920039200392003920039
8002420038155000392580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010005020011600112003580000102003920039200392003920039