derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
102 lines
3.8 KiB
LLVM
102 lines
3.8 KiB
LLVM
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 < %s | \
|
|
; RUN: FileCheck %s -check-prefix=CHECK-LE
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 < %s | \
|
|
; RUN: FileCheck %s -check-prefix=CHECK-BE
|
|
|
|
; Check for a vector merge instruction using two inputs
|
|
; The shufflevector specifies the even elements, using big endian element
|
|
; ordering. If run on a big endian machine, this should produce the vmrgew
|
|
; instruction. If run on a little endian machine, this should produce the
|
|
; vmrgow instruction. Note also that on little endian the input registers
|
|
; are swapped also.
|
|
define void @check_merge_even_xy(ptr %A, ptr %B) {
|
|
entry:
|
|
; CHECK-LE-LABEL: @check_merge_even_xy
|
|
; CHECK-BE-LABEL: @check_merge_even_xy
|
|
%tmp = load <16 x i8>, ptr %A
|
|
%tmp2 = load <16 x i8>, ptr %B
|
|
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2,
|
|
<16 x i32> <i32 0, i32 1, i32 2, i32 3,
|
|
i32 16, i32 17, i32 18, i32 19,
|
|
i32 8, i32 9, i32 10, i32 11,
|
|
i32 24, i32 25, i32 26, i32 27>
|
|
; CHECK-LE: vmrgow 2, 3, 2
|
|
; CHECK-BE: vmrgew 2, 2, 3
|
|
store <16 x i8> %tmp3, ptr %A
|
|
ret void
|
|
; CHECK-LE: blr
|
|
; CHECK-BE: blr
|
|
}
|
|
|
|
; Check for a vector merge instruction using a single input.
|
|
; The shufflevector specifies the even elements, using big endian element
|
|
; ordering. If run on a big endian machine, this should produce the vmrgew
|
|
; instruction. If run on a little endian machine, this should produce the
|
|
; vmrgow instruction.
|
|
define void @check_merge_even_xx(ptr %A) {
|
|
entry:
|
|
; CHECK-LE-LABEL: @check_merge_even_xx
|
|
; CHECK-BE-LABEL: @check_merge_even_xx
|
|
%tmp = load <16 x i8>, ptr %A
|
|
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp,
|
|
<16 x i32> <i32 0, i32 1, i32 2, i32 3,
|
|
i32 0, i32 1, i32 2, i32 3,
|
|
i32 8, i32 9, i32 10, i32 11,
|
|
i32 8, i32 9, i32 10, i32 11>
|
|
; CHECK-LE: vmrgow 2, 2, 2
|
|
; CHECK-BE: vmrgew 2, 2, 2
|
|
store <16 x i8> %tmp2, ptr %A
|
|
ret void
|
|
; CHECK-LE: blr
|
|
; CHECK-BE: blr
|
|
}
|
|
|
|
; Check for a vector merge instruction using two inputs.
|
|
; The shufflevector specifies the odd elements, using big endian element
|
|
; ordering. If run on a big endian machine, this should produce the vmrgow
|
|
; instruction. If run on a little endian machine, this should produce the
|
|
; vmrgew instruction. Note also that on little endian the input registers
|
|
; are swapped also.
|
|
define void @check_merge_odd_xy(ptr %A, ptr %B) {
|
|
entry:
|
|
; CHECK-LE-LABEL: @check_merge_odd_xy
|
|
; CHECK-BE-LABEL: @check_merge_odd_xy
|
|
%tmp = load <16 x i8>, ptr %A
|
|
%tmp2 = load <16 x i8>, ptr %B
|
|
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2,
|
|
<16 x i32> <i32 4, i32 5, i32 6, i32 7,
|
|
i32 20, i32 21, i32 22, i32 23,
|
|
i32 12, i32 13, i32 14, i32 15,
|
|
i32 28, i32 29, i32 30, i32 31>
|
|
; CHECK-LE: vmrgew 2, 3, 2
|
|
; CHECK-BE: vmrgow 2, 2, 3
|
|
store <16 x i8> %tmp3, ptr %A
|
|
ret void
|
|
; CHECK-LE: blr
|
|
; CHECK-BE: blr
|
|
}
|
|
|
|
; Check for a vector merge instruction using a single input.
|
|
; The shufflevector specifies the odd elements, using big endian element
|
|
; ordering. If run on a big endian machine, this should produce the vmrgow
|
|
; instruction. If run on a little endian machine, this should produce the
|
|
; vmrgew instruction.
|
|
define void @check_merge_odd_xx(ptr %A) {
|
|
entry:
|
|
; CHECK-LE-LABEL: @check_merge_odd_xx
|
|
; CHECK-BE-LABEL: @check_merge_odd_xx
|
|
%tmp = load <16 x i8>, ptr %A
|
|
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp,
|
|
<16 x i32> <i32 4, i32 5, i32 6, i32 7,
|
|
i32 4, i32 5, i32 6, i32 7,
|
|
i32 12, i32 13, i32 14, i32 15,
|
|
i32 12, i32 13, i32 14, i32 15>
|
|
; CHECK-LE: vmrgew 2, 2, 2
|
|
; CHECK-BE: vmrgow 2, 2, 2
|
|
store <16 x i8> %tmp2, ptr %A
|
|
ret void
|
|
; CHECK-LE: blr
|
|
; CHECK-BE: blr
|
|
}
|
|
|