Skip to content

[LoongArch] Pre-commit for widen shuffle mask #136544

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Apr 23, 2025
Merged

[LoongArch] Pre-commit for widen shuffle mask #136544

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2fdc96c
Pre-commit for widen shuffle mask
tangaac Apr 21, 2025
37dc6a4
add more tests
tangaac Apr 23, 2025
cecffd3
Merge branch 'main' into pre-widen-shuffle-mask
tangaac Apr 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
71 changes: 71 additions & 0 deletions llvm/test/CodeGen/LoongArch/lasx/widen-shuffle-mask.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc --mtriple=loongarch64 --mattr=+lasx < %s | FileCheck %s

define <32 x i8> @widen_shuffle_mask_v32i8_to_v16i16(<32 x i8> %a, <32 x i8> %b) {
; CHECK-LABEL: widen_shuffle_mask_v32i8_to_v16i16:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI0_0)
; CHECK-NEXT: xvld $xr2, $a0, %pc_lo12(.LCPI0_0)
; CHECK-NEXT: xvshuf.b $xr0, $xr1, $xr0, $xr2
; CHECK-NEXT: ret
%r = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 32, i32 33, i32 34, i32 35, i32 24, i32 25, i32 26, i32 27, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 60, i32 61, i32 30, i32 31>
ret <32 x i8> %r
}

define <32 x i8> @widen_shuffle_mask_v32i8_to_v8i32(<32 x i8> %a, <32 x i8> %b) {
; CHECK-LABEL: widen_shuffle_mask_v32i8_to_v8i32:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI1_0)
; CHECK-NEXT: xvld $xr2, $a0, %pc_lo12(.LCPI1_0)
; CHECK-NEXT: xvshuf.b $xr0, $xr1, $xr0, $xr2
; CHECK-NEXT: ret
%r = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 32, i32 33, i32 34, i32 35, i32 24, i32 25, i32 26, i32 27, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 60, i32 61, i32 62, i32 63>
ret <32 x i8> %r
}

define <32 x i8> @widen_shuffle_mask_v32i8_to_v4i64(<32 x i8> %a, <32 x i8> %b) {
; CHECK-LABEL: widen_shuffle_mask_v32i8_to_v4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_0)
; CHECK-NEXT: xvld $xr2, $a0, %pc_lo12(.LCPI2_0)
; CHECK-NEXT: xvshuf.b $xr0, $xr1, $xr0, $xr2
; CHECK-NEXT: ret
%r = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55>
ret <32 x i8> %r
}

define <16 x i16> @widen_shuffle_mask_v16i16_to_v8i32(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: widen_shuffle_mask_v16i16_to_v8i32:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI3_0)
; CHECK-NEXT: xvld $xr2, $a0, %pc_lo12(.LCPI3_0)
; CHECK-NEXT: xvshuf.h $xr2, $xr1, $xr0
; CHECK-NEXT: xvori.b $xr0, $xr2, 0
; CHECK-NEXT: ret
%r = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 1, i32 6, i32 7, i32 16, i32 17, i32 2, i32 3, i32 10, i32 11, i32 12, i32 13, i32 24, i32 25, i32 26, i32 27>
ret <16 x i16> %r
}

define <16 x i16> @widen_shuffle_mask_v16i16_to_v4i64(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: widen_shuffle_mask_v16i16_to_v4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI4_0)
; CHECK-NEXT: xvld $xr2, $a0, %pc_lo12(.LCPI4_0)
; CHECK-NEXT: xvshuf.h $xr2, $xr1, $xr0
; CHECK-NEXT: xvori.b $xr0, $xr2, 0
; CHECK-NEXT: ret
%r = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 20, i32 21, i32 22, i32 23, i32 12, i32 13, i32 14, i32 15, i32 28, i32 29, i32 30, i32 31>
ret <16 x i16> %r
}

define <8 x i32> @widen_shuffle_mask_v8i32_to_v4i64(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: widen_shuffle_mask_v8i32_to_v4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI5_0)
; CHECK-NEXT: xvld $xr2, $a0, %pc_lo12(.LCPI5_0)
; CHECK-NEXT: xvshuf.w $xr2, $xr1, $xr0
; CHECK-NEXT: xvori.b $xr0, $xr2, 0
; CHECK-NEXT: ret
%r = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 14, i32 15, i32 6, i32 7>
ret <8 x i32> %r
}
71 changes: 71 additions & 0 deletions llvm/test/CodeGen/LoongArch/lsx/widen-shuffle-mask.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s

define <16 x i8> @widen_shuffle_mask_v16i8_to_v8i16(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: widen_shuffle_mask_v16i8_to_v8i16:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI0_0)
; CHECK-NEXT: vld $vr2, $a0, %pc_lo12(.LCPI0_0)
; CHECK-NEXT: vshuf.b $vr0, $vr1, $vr0, $vr2
; CHECK-NEXT: ret
%r = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 1, i32 24, i32 25, i32 26, i32 27, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19, i32 2, i32 3>
ret <16 x i8> %r
}

define <16 x i8> @widen_shuffle_mask_v16i8_to_v4i32(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: widen_shuffle_mask_v16i8_to_v4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI1_0)
; CHECK-NEXT: vld $vr2, $a0, %pc_lo12(.LCPI1_0)
; CHECK-NEXT: vshuf.b $vr0, $vr1, $vr0, $vr2
; CHECK-NEXT: ret
%r = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 24, i32 25, i32 26, i32 27, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
ret <16 x i8> %r
}

define <16 x i8> @widen_shuffle_mask_v16i8_to_v2i64(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: widen_shuffle_mask_v16i8_to_v2i64:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI2_0)
; CHECK-NEXT: vld $vr2, $a0, %pc_lo12(.LCPI2_0)
; CHECK-NEXT: vshuf.b $vr0, $vr1, $vr0, $vr2
; CHECK-NEXT: ret
%r = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
ret <16 x i8> %r
}

define <8 x i16> @widen_shuffle_mask_v8i16_to_v4i32(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: widen_shuffle_mask_v8i16_to_v4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI3_0)
; CHECK-NEXT: vld $vr2, $a0, %pc_lo12(.LCPI3_0)
; CHECK-NEXT: vshuf.h $vr2, $vr1, $vr0
; CHECK-NEXT: vori.b $vr0, $vr2, 0
; CHECK-NEXT: ret
%r = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 1, i32 12, i32 13, i32 14, i32 15, i32 2, i32 3>
ret <8 x i16> %r
}

define <8 x i16> @widen_shuffle_mask_v8i16_to_v2i64(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: widen_shuffle_mask_v8i16_to_v2i64:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI4_0)
; CHECK-NEXT: vld $vr2, $a0, %pc_lo12(.LCPI4_0)
; CHECK-NEXT: vshuf.h $vr2, $vr1, $vr0
; CHECK-NEXT: vori.b $vr0, $vr2, 0
; CHECK-NEXT: ret
%r = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
ret <8 x i16> %r
}

define <4 x i32> @widen_shuffle_mask_v4i32_to_v2i64(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: widen_shuffle_mask_v4i32_to_v2i64:
; CHECK: # %bb.0:
; CHECK-NEXT: pcalau12i $a0, %pc_hi20(.LCPI5_0)
; CHECK-NEXT: vld $vr2, $a0, %pc_lo12(.LCPI5_0)
; CHECK-NEXT: vshuf.w $vr2, $vr1, $vr0
; CHECK-NEXT: vori.b $vr0, $vr2, 0
; CHECK-NEXT: ret
%r = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
ret <4 x i32> %r
}
Loading