Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

UADDW (vector, 8H)

Test 1: uops

Code:

  uaddw v0.8h, v0.8h, v1.8b
  movi v0.16b, 1
  movi v1.16b, 2

(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)03081e3a3f4e51inst 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)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150026616872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
100420371500289168725100010001000264680120182037203715723189510001000200020372037111001100002477416441787100020382038203820382038
1004203716002112168725100010001000264680120182037203715723189510001000200020372037111001100001577416441787100020382038203820382038
100420371500266168725100010001000264680120182037203715723189510001000200020372037111001100001577416441787100020382038203820382038
10042037150026616872510001000100026468012018203720371572318951000100020002037203711100110000377416441787100020382038203820382038
100420371500266168725100010001000264680120182037203715723189510001000200020372037111001100001277416441787100020382038203820382038
100420371500211016872510001000100026468012018203720371572318951000100020002037203711100110001077416441787100020382038203820382038
10042037150328916872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
10042037150026616872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038
10042037160026616872510001000100026468012018203720371572318951000100020002037203711100110000077416441787100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddw v0.8h, v0.8h, v1.8b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst 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)~map lookup fp/simd (81)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)9fa6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715007261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100008007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318765101002001000020020000200372003711102011009910010010000100000037101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)~map lookup fp/simd (81)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)9fa1a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000300640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000200640216221978510000102003820038200382003820038
10024200371500089196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000400640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000300640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000103640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000100640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uaddw v0.8h, v1.8h, v0.8b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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)6061696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)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)9fa1a6a8acc2cdcfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000961196872510100100100001001000050028476801020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710002162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710002162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710002162219791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768010200182003720037184223187451010020010000200200002003720037111020110099100100100001002034300710002162219791100001002003820038200382003820038
1020420037150000251196872510100100100001001000050028476801020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710002162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710002162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710002162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000710002162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100021000710002162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100001000710002162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst 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)~map lookup fp/simd (81)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500103196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001003640316221978510000102003820038200382003820038
10024200371500170196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500124196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500168196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150084196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500105196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500441196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uaddw v0.8h, v8.8h, v9.8b
  uaddw v1.8h, v8.8h, v9.8b
  uaddw v2.8h, v8.8h, v9.8b
  uaddw v3.8h, v8.8h, v9.8b
  uaddw v4.8h, v8.8h, v9.8b
  uaddw v5.8h, v8.8h, v9.8b
  uaddw v6.8h, v8.8h, v9.8b
  uaddw v7.8h, v8.8h, v9.8b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b181e3f51inst 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)~map lookup fp/simd (81)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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000386258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051104162320035800001002003920039200392003920039
802042003815000061258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103162320035800001002003920039200392003920039
8020420038150000191258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103163220035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103163320035800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010010051103163220035800001002003920039200392003920039
80204200381500001517258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010001051103163220035800001002003920039200392003920039
802042003815010040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103163320035800001002003920039200392003920039
8020420038150000524258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010002051102162320035800001002003920039200392003920039
802042003815000084258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103163320035800001002003920039200392003920039
8020420038150000189258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103163220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)~map lookup fp/simd (81)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)9fa1a6a8a9acc2cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000000006225800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100040005020616015320035080000102003920039200392003920039
800242003815000000000324258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001002006605020316016520035080000102003920039200392003920039
8002420038150001000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000005020316018520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000005020316015520035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000502051606520035080000102003920039200392003920039
800242003815000000000111325800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000005020516016320035080000102003920039200392003920039
80024200381500000000015125800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000305020516017520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000005020516021420035080000102003920039200392003920039
8002420038150000000001252580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000502041605520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000005020516021320035080000102003920039200392003920039