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, 4S, lsl)

Test 1: uops

Code:

  movi v0.4s, #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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004288204025100010001000700012692882881233146100010002882881110011000073216222851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073216222851000289289289289289
1004288204925100010001000700012692882881233146100010002882881110011000073216222851000289289289289289
1004288294025100010001000700002692882881233146100010002882881110011000073216222851000289289289289289
1004288304025100010001000700002692882881233146100010002882881110011000073216222851000289289289289289
1004288304025100010001000700012692882881233146100010002882881110011000073216222851000289289289289289
1004288204025100010001000700002692882881233146100010002882881110011000073216222851000289289289289289
1004288204025100010001000700012692882881233146100010002882881110011000073216222851000289289289289289
1004288204025100010001000700012692882881233146100010002882881110011000073216222851000289289289289289
1004288204025100010001000700012692882881233146100010002882881110011000073216222851000289289289289289

Test 2: throughput

Count: 8

Code:

  movi v0.4s, #3, lsl #8
  movi v1.4s, #3, lsl #8
  movi v2.4s, #3, lsl #8
  movi v3.4s, #3, lsl #8
  movi v4.4s, #3, lsl #8
  movi v5.4s, #3, lsl #8
  movi v6.4s, #3, lsl #8
  movi v7.4s, #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)03191e3a3f51inst 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)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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381500004025801001008000010080000500560000020019200382003899730399968010020080000200200382003811802011009910010080000100000051104163520035800001002003920039200392003920039
80204200381500004025801001008000010080000500560000120019200382003899730399968010020080000200200382003811802011009910010080000100000051105165320035800001002003920039200392003920039
80204200381500004025801001008000010080000500560000120019200382003899730399968010020080000200200382003811802011009910010080000100002951106165620035800001002003920039200392003920039
8020420038150024040258010010080000100800005005600001200192003820038997303999680100200800002002003820038118020110099100100800001000024051106166320035800001002003920039200392003920039
80204200381500004025801001008000010080000500560000020019200382003899730399968010020080000200200382003811802011009910010080000100000051105165520035800001002003920039200392003920039
80204200381500004025801001008000010080000500560000020019200382003899730399968010020080000200200382003811802011009910010080000100000051105165520035800001002003920039200392003920039
80204200381500004025801001008000010080000500560000020019200382003899730399968010020080000200200382003811802011009910010080000100000651105165520035800001002003920039200392003920039
80204200381490004025801001008000010080000500560000020019200382003899730399968010020080000200200382003811802011009910010080000100001651105165320035800001002003920039201122003920039
80204200381500004025801001008000010080000500560000020019200382003899730399968010020080000200200382003811802011009910010080000100003951106165520035800001002003920039200392003920039
80204200381500004025801001008000010080000500560000020019200382003899730399968010020080000200200382003811802011009910010080000100000351106165520035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481550096039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020316222003580000102003920039200392003920039
80024200381560084039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020216222003580000102003920039200392003920039
8002420038156000039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020216222003580000102003920039200392003920039
80024200381550075039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020216222003580000102003920039200392003920039
8002420038155000039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020216222003580000102003920039200392003920039
8002420038156000039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020316222003580000102003920039200392003920039
8002420038155000060258001010800001080000555600001200192003820038999631001880010208000020200382003811800211091010800001035020216222003580000102003920039200392003920039
800242003815500303039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020216222003580000102003920039200392003920039
8002420038155003930392580010108000010800005056000002001920038200381000931001880010208000020200382003811800211091010800001005020216222003580000102003920039200392003920039
800242003815500354039258001010800001080000505600000200192003820038999631001880010208000020200382003811800211091010800001005020316222003580000102003920039200392003920039