petrbalvin
cfc3abb752
feat(asm): encode the remaining amd64 VEX families
...
The SSE3 horizontal and add-subtract pairs, the SSSE3 sign and
horizontal integers, the masked moves in both directions, the
reciprocity and test pairs, the AVX imm8 tail (blends, dot products,
inserts, rounds, MPSADBW, the string compares), the four-operand
variable blends with their /is4 mask byte, the scalar three-operand
moves, the MXCSR accessors, the VPERMIL register controls and the
variable word shifts, plus the BMI2 count forms over memory. Every
encoding is pinned byte for byte against go tool asm through every
corpus line the toolchain's own amd64enc.s carries for the families
(852 lines); the /is4 byte carries the mask register number in its high
nibble, the layout the toolchain emits.
Assisted-by: GLM 5.3 Flash
2026-10-06 23:59:47 +02:00
petrbalvin
bc4ac93fd9
style(asm): reindent the evex comment gofmt asks for
...
Test / test (push) Failing after 21m29s
Assisted-by: GLM 5.3
2026-10-02 00:41:46 +02:00
petrbalvin
bafb2fd130
feat(asm): encode the amd64 and loong64 tails of the corpus testdata
...
Assisted-by: GLM 5.3
2026-10-02 00:40:43 +02:00
petrbalvin
bfb7701db1
feat(amd64): emit the quad-register EVEX families
...
Assisted-by: GLM 5.3 Flash
2026-09-21 02:02:19 +02:00
petrbalvin
81e2673923
feat(amd64): encode the AVX-512 and BMI corpus families
...
Assisted-by: GLM 5.3 Flash
2026-09-20 21:17:20 +02:00
petrbalvin
fc2d92eabd
feat(amd64): encode the GOROOT instruction families
...
Assisted-by: GLM 5.3 Flash
2026-09-20 06:44:51 +02:00
petrbalvin
4258131a3a
fix(amd64): correct guard displacements, frameless FP offsets and immediate ranges
...
Assisted-by: GLM 5.3
2026-09-19 23:49:07 +02:00
petrbalvin
1691c81095
style: replace em and en dashes across sources
2026-09-14 18:22:18 +02:00
petrbalvin
56ad158772
fix: restore iota blocks, asm --format flag and prose after the syntax pass
Test / vet (push) Successful in 48s
Test / test (push) Successful in 2m35s
Test / build (push) Successful in 40s
2026-08-29 17:12:53 +02:00
petrbalvin
9beff4ae85
style: modernize to splitseq, cut, min, maps.copy and range-over-int
2026-08-29 16:04:32 +02:00
petrbalvin
19a26e049b
feat(asm): add vpcmp compare, full opmask set, legacy sse integers and bswap
...
Test / vet (push) Successful in 47s
Test / test (push) Successful in 2m35s
Test / build (push) Successful in 41s
Assisted-by: GLM 5.3
2026-08-27 22:41:03 +02:00
petrbalvin
5af12e15ac
feat(asm): add the GPR-interchanging conversions, completing the amd64 EVEX set
...
Assisted-by: Qwen 3.8 Max Preview
2026-08-02 23:11:30 +02:00
petrbalvin
1312122a99
feat(asm): complete the EVEX conversions, narrowing and mask-vector moves
...
Assisted-by: Qwen 3.8 Max Preview
2026-07-20 16:05:08 +02:00
petrbalvin
11f962fbcc
feat(asm): add the EVEX FP helper tail and gather/scatter with VSIB
...
Assisted-by: Qwen 3.8 Max Preview
2026-07-19 15:58:48 +02:00
petrbalvin
ee68859beb
feat(asm): add the wider EVEX set and the rounding, SAE and broadcast suffixes
...
Assisted-by: Qwen 3.8 Max Preview
2026-07-18 15:47:59 +02:00
petrbalvin
b914c0e390
feat(asm): add the EVEX floating-point and conversion set
...
Assisted-by: Qwen 3.8 Max Preview
2026-07-15 17:13:28 +02:00
petrbalvin
0f3146ff2c
feat(asm): add EVEX masking, zeroing and the AVX-512 F/BW integer set
...
Assisted-by: Qwen 3.8 Max Preview
2026-07-14 21:03:26 +02:00
petrbalvin
1a01870695
fix(lint): calibrate register-clobber to the Go ABI and add legacy SSE moves
...
Assisted-by: Qwen 3.8 Max Preview
2026-07-11 17:36:52 +02:00
petrbalvin
458cfb626e
feat(asm): add EVEX/AVX-512 encoding and assemble the AVX-512 kernel byte-identically
...
Assisted-by: Qwen 3.8 Max Preview
2026-07-10 13:20:49 +02:00
petrbalvin