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, 64-bit, 2D)

Test 1: uops

Code:

  movi v0.2d, #0xff00

(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)033f51inst 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
1004288240251000100010007000126928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000126928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000126928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000126928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000126928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000126928828812331461000100028828811100110000073116112851000289289289289289
1004288240251000100010007000026928828812331461000100028828811100110000073116112851000289289289289289
1004288340251000100010007000126928828812331461000100028828811100110000073116112851000289289289289289

Test 2: throughput

Count: 8

Code:

  movi v0.2d, #0xff00
  movi v1.2d, #0xff00
  movi v2.2d, #0xff00
  movi v3.2d, #0xff00
  movi v4.2d, #0xff00
  movi v5.2d, #0xff00
  movi v6.2d, #0xff00
  movi v7.2d, #0xff00

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b191e3f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815500040258010010080000100800005005600002001920038200899973399968010020080000200200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815500040258010010080000100800005005600002001920038200389973399968010020080098200200382003811802011009910010080000100000000514621622200350800001002003920039200392003920039
802042003815500082258010010080000100800005005600002001920038200389973399968010020080000200200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815500040258010010080000100800005005600002001920038200389973399968010020080000200200382003811802011009910010080000100000000511021622200350800001002003920039200912003920039
802042003815600040258010010080000100800005005600002001920038200389973399968010020080000200200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815500040258010010080000100800005005600002001920038200389973399968010020080000200200882003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815500061258030712180000100800005005600002001920038200389973399968010020080000200200382003811802011009910010080000100000000511054400200350800001002003920039200392003920039
802042003815600029258010810080008100800205005601282009720038200389987699898033620280032200200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
802042003815600029258010810080008100800205005601282001920038200389977699898012020080032200200382003811802011009910010080000100010111511801600200350800001002003920039200392003920039
8020420038155003409258010810080008100800205005601282001920038200389977699898012020080032200200382003811802011009910010080000100200111511802800200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b181e1f3f5051inst 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)9fa0a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040155000000390258001010800001080000505600001200192003820038999631001880010208000020200382003811800211091010800001000000005020101664200353680000102003920039200392003920039
800242003815500000039025800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100000200502061612520035080000102003920039200392003920039
80024200381550000003902580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000000050206166620035080000102003920039200392003920039
800242003815631000039025800101080000108000050560000020019200382003899963100188001020800002020038200381180021109101080000100103000502061641020035080000102003920039200392003920039
8002420038155000000683025800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100000000502041651020035080000102003920039200392003920039
800242003815600000081025800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100000000502011166520035080000102003920039200392003920039
80024200381550010003902580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010000000050566166520035080000102003920039200392003920039
800242003815600000039025800101080000108000050560000120019200382003899963100188001020800002020038200381180021109101080000100001195000502041655200352080000102003920039200392003920039
80024200381550000003902580010108000010800005056000002001920038200389996310018800102080000202003820038118002110910108000010000114000502051651120035080000102003920039200392003920039
80024200381550000003902580010108000010800005056000012001920038200389996310018800102080000202003820038118002110910108000010000000050204164920035080000102003920039200392003920039