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)

Test 1: uops

Code:

  movi v0.4h, #3

(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)696d6edispatch 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042882040251000100010007000269288288123314610001000288288111001100073216112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882040251000100010007000269288288123314610001000288288111001100073116112851000289289289289289
10042882340251000100010007000269288288123314610001000288288111001100073116112851000289289289289289

Test 2: throughput

Count: 8

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815600402580100100800001008000050056000002001920038200389973399968010020080000200200382003811802011009910010080000100042951102162220035800001002003920039200392003920039
802042003815600402580100100800001008000050056000012001920038200389973399968010020080000200200382003811802011009910010080000100000651102162220035800001002003920039200392003920039
802042003816103402580773100800001008000050056000002001920038200389973399968010020080000200200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
80204200381560040258010010080000100800005005600000200192003820038997339996801002008000020020038200381180201100991001008000010003901551102162220035800001002003920039200392003920039
802042003815500402580100100800001008000050056000002001920038200389973399968010020080000200200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
802042003815500402580100100800001008000050056000002001920038200389973399968010020080000200200382003811802011009910010080000100000651102162220035800001002003920039200392003920039
802042003815500402580100100800001008000050056000002001920086200389973399968010020080000200200382003811802011009910010080000100010351102162220035800001002003920039200392003920039
802042003815500402580100100800001008000050056000002001920038200389973399968010020080000200200382003811802011009910010080000100010051102162220035800001002003920039200392003920039
8020420038155004025801001008000010080000500560000020019200382003899733999680100200800002002003820038118020110099100100800001000101251102162220035800001002003920039200392003920039
802042003815600402580100100800001008000050056000012001920038200389973399968010020080000200200382003811802011009910010080000100080051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040708090a0b18191e1f3a3f51inst 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)72scheduler 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)9fa0a1a6a7a8a9acc2cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715600000000000392580010108000010800005056000020019200382024299960310018800102080000202003820038118002110910108000010000000150502022160242420035080000102003920039200392003920039
80024200381610000000000039258001010800001080000505600002001920038200389996031001880010208000020200382003811800211091010800001000003090502025160252520035080000102003920039200392003920039
80024200381610000000052800392580010108000010800005056000020019200382003899960310018800102080000202003820038118002110910108000010000000780502027160262620035080000102003920039200392003920039
800242003816000000000000392580010108000010800005056000020019200382003899960310018800102080000202003820038118002110910108000010000000210502012160271620035080000102003920039200392003920039
80024200381600000000000039258001010800001080000505600002001920038200389996031001880010208000020200382003811800211091010800001000004000502016160271620035080000102003920039200392003920039
800242003816100000000000392580010108000010800005056000020019200382003899960310018800102080000202003820038118002110910108000010000000720502026160152720035080000102003920039200392003920039
80024200381610000000000039258001010800001080000505600002001920038200389996031001880010208000020200382003811800211091010800001000000060502017160272720035080000102003920039200392003920039
80024200381610120000000001016258001010800001080000505600002001920038200389996031001880010208000020200382003811800211091010800001000006030502025160202520035080000102003920039200392004220039
800242003816100000000000392580010108000010800005056000020019200382003899960310018800102080000202003820038118002110910108000010000000390502028160152520035080000102003920039200392003920039
80024200381610000000000039258001010800001080000505600002001920038200389996031001880010208000020200382003811800211091010800001000001030502027160152720035080000102003920039200392003920039