T0b1/wasmtime
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

x64: Improve memory support in {insert,extract}lane (#5982)

Browse Source 
* x64: Improve memory support in `{insert,extract}lane`

This commit improves adds support to Cranelift to emit `pextr{b,w,d,q}`
with a memory destination, merging a store-of-extract operation into one
instruction. Additionally AVX support is added for the `pextr*`
instructions.

I've additionally tried to ensure that codegen tests and runtests exist
for all forms of these instructions too.

* Add missing commas

* Fix tests
This commit is contained in:
Alex Crichton
2023-03-13 14:30:44 -05:00
committed by GitHub
parent 5c95e6fbaf
commit 6ecdc2482e
17 changed files with 1066 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
cranelift/filetests/filetests/wasm/x64-relaxed-simd-deterministic.wat
View File

@@ -44,7 +44,7 @@
;; movq %rsp, %rbp
;; unwind DefineNewFrame { offset_upward_to_caller_sp: 16, offset_downward_to_clobbers: 0 }
;; block0:
;; vcmpps $0 %xmm0, %xmm0, %xmm3
;; vcmpps $0, %xmm0, %xmm0, %xmm3
;; vandps %xmm0, %xmm3, %xmm5
;; vpxor %xmm3, %xmm5, %xmm7
;; vcvttps2dq %xmm5, %xmm9
@@ -71,7 +71,7 @@
;; vcvtdq2ps %xmm11, %xmm13
;; vcvttps2dq %xmm7, %xmm15
;; vsubps %xmm7, %xmm13, %xmm1
;; vcmpps $2 %xmm13, %xmm1, %xmm3
;; vcmpps $2, %xmm13, %xmm1, %xmm3
;; vcvttps2dq %xmm1, %xmm5
;; vpxor %xmm5, %xmm3, %xmm7
;; uninit %xmm9
@@ -90,7 +90,7 @@
;; movq %rsp, %rbp
;; unwind DefineNewFrame { offset_upward_to_caller_sp: 16, offset_downward_to_clobbers: 0 }
;; block0:
;; vcmppd $0 %xmm0, %xmm0, %xmm3
;; vcmppd $0, %xmm0, %xmm0, %xmm3
;; vandps %xmm3, const(0), %xmm5
;; vminpd %xmm0, %xmm5, %xmm7
;; vcvttpd2dq %xmm7, %xmm0
@@ -112,7 +112,7 @@
;; vminpd %xmm7, const(0), %xmm9
;; vroundpd $3, %xmm9, %xmm11
;; vaddpd %xmm11, const(1), %xmm13
;; vshufps $136 %xmm13, %xmm5, %xmm0
;; vshufps $136, %xmm13, %xmm5, %xmm0
;; jmp label1
;; block1:
;; movq %rbp, %rsp
@@ -128,9 +128,9 @@
;; vpmovsxbw %xmm0, %xmm10
;; vpmovsxbw %xmm1, %xmm12
;; vpmullw %xmm10, %xmm12, %xmm14
;; vpalignr $8 %xmm0, %xmm0, %xmm8
;; vpalignr $8, %xmm0, %xmm0, %xmm8
;; vpmovsxbw %xmm8, %xmm10
;; vpalignr $8 %xmm1, %xmm1, %xmm12
;; vpalignr $8, %xmm1, %xmm1, %xmm12
;; vpmovsxbw %xmm12, %xmm15
;; vpmullw %xmm10, %xmm15, %xmm0
;; vphaddw %xmm14, %xmm0, %xmm0
@@ -149,9 +149,9 @@
;; vpmovsxbw %xmm0, %xmm13
;; vpmovsxbw %xmm1, %xmm15
;; vpmullw %xmm13, %xmm15, %xmm3
;; vpalignr $8 %xmm0, %xmm0, %xmm11
;; vpalignr $8, %xmm0, %xmm0, %xmm11
;; vpmovsxbw %xmm11, %xmm13
;; vpalignr $8 %xmm1, %xmm1, %xmm15
;; vpalignr $8, %xmm1, %xmm1, %xmm15
;; vpmovsxbw %xmm15, %xmm1
;; vpmullw %xmm13, %xmm1, %xmm4
;; vphaddw %xmm3, %xmm4, %xmm15