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
181 lines
5.5 KiB
LLVM
181 lines
5.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -verify-machineinstrs -mattr=+simd128 | FileCheck %s
|
|
|
|
; Test that a vector trunc correctly optimizes and lowers to narrow instructions
|
|
|
|
target triple = "wasm32-unknown-unknown"
|
|
|
|
define <16 x i8> @trunc16i64_16i8(<16 x i64> %a) {
|
|
; CHECK-LABEL: trunc16i64_16i8:
|
|
; CHECK: .functype trunc16i64_16i8 (v128, v128, v128, v128, v128, v128, v128, v128) -> (v128)
|
|
; CHECK-NEXT: .local v128
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: v128.const 255, 255
|
|
; CHECK-NEXT: local.tee 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 1
|
|
; CHECK-NEXT: local.get 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: local.get 2
|
|
; CHECK-NEXT: local.get 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 3
|
|
; CHECK-NEXT: local.get 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: local.get 4
|
|
; CHECK-NEXT: local.get 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 5
|
|
; CHECK-NEXT: local.get 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: local.get 6
|
|
; CHECK-NEXT: local.get 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 7
|
|
; CHECK-NEXT: local.get 8
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: i8x16.narrow_i16x8_u
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <16 x i64> %a to <16 x i8>
|
|
ret <16 x i8> %0
|
|
}
|
|
|
|
define <16 x i8> @trunc16i32_16i8(<16 x i32> %a) {
|
|
; CHECK-LABEL: trunc16i32_16i8:
|
|
; CHECK: .functype trunc16i32_16i8 (v128, v128, v128, v128) -> (v128)
|
|
; CHECK-NEXT: .local v128
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: v128.const 255, 255, 255, 255
|
|
; CHECK-NEXT: local.tee 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 1
|
|
; CHECK-NEXT: local.get 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: local.get 2
|
|
; CHECK-NEXT: local.get 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 3
|
|
; CHECK-NEXT: local.get 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: i8x16.narrow_i16x8_u
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <16 x i32> %a to <16 x i8>
|
|
ret <16 x i8> %0
|
|
}
|
|
|
|
define <16 x i8> @trunc16i16_16i8(<16 x i16> %a) {
|
|
; CHECK-LABEL: trunc16i16_16i8:
|
|
; CHECK: .functype trunc16i16_16i8 (v128, v128) -> (v128)
|
|
; CHECK-NEXT: .local v128
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: v128.const 255, 255, 255, 255, 255, 255, 255, 255
|
|
; CHECK-NEXT: local.tee 2
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 1
|
|
; CHECK-NEXT: local.get 2
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i8x16.narrow_i16x8_u
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <16 x i16> %a to <16 x i8>
|
|
ret <16 x i8> %0
|
|
}
|
|
|
|
define <8 x i8> @trunc8i16_8i8(<8 x i16> %a) {
|
|
; CHECK-LABEL: trunc8i16_8i8:
|
|
; CHECK: .functype trunc8i16_8i8 (v128) -> (v128)
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: i8x16.shuffle 0, 2, 4, 6, 8, 10, 12, 14, 0, 0, 0, 0, 0, 0, 0, 0
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <8 x i16> %a to <8 x i8>
|
|
ret <8 x i8> %0
|
|
}
|
|
|
|
define <8 x i16> @trunc8i64_8i16(<8 x i64> %a) {
|
|
; CHECK-LABEL: trunc8i64_8i16:
|
|
; CHECK: .functype trunc8i64_8i16 (v128, v128, v128, v128) -> (v128)
|
|
; CHECK-NEXT: .local v128
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: v128.const 65535, 65535
|
|
; CHECK-NEXT: local.tee 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 1
|
|
; CHECK-NEXT: local.get 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: local.get 2
|
|
; CHECK-NEXT: local.get 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 3
|
|
; CHECK-NEXT: local.get 4
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <8 x i64> %a to <8 x i16>
|
|
ret <8 x i16> %0
|
|
}
|
|
|
|
define <8 x i16> @trunc8i32_8i16(<8 x i32> %a) {
|
|
; CHECK-LABEL: trunc8i32_8i16:
|
|
; CHECK: .functype trunc8i32_8i16 (v128, v128) -> (v128)
|
|
; CHECK-NEXT: .local v128
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: v128.const 65535, 65535, 65535, 65535
|
|
; CHECK-NEXT: local.tee 2
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: local.get 1
|
|
; CHECK-NEXT: local.get 2
|
|
; CHECK-NEXT: v128.and
|
|
; CHECK-NEXT: i16x8.narrow_i32x4_u
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <8 x i32> %a to <8 x i16>
|
|
ret <8 x i16> %0
|
|
}
|
|
|
|
define <4 x i16> @trunc4i32_4i16(<4 x i32> %a) {
|
|
; CHECK-LABEL: trunc4i32_4i16:
|
|
; CHECK: .functype trunc4i32_4i16 (v128) -> (v128)
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: i8x16.shuffle 0, 1, 4, 5, 8, 9, 12, 13, 0, 1, 0, 1, 0, 1, 0, 1
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <4 x i32> %a to <4 x i16>
|
|
ret <4 x i16> %0
|
|
}
|
|
|
|
define <4 x i8> @trunc4i32_4i8(<4 x i32> %a) {
|
|
; CHECK-LABEL: trunc4i32_4i8:
|
|
; CHECK: .functype trunc4i32_4i8 (v128) -> (v128)
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: local.get 0
|
|
; CHECK-NEXT: i8x16.shuffle 0, 4, 8, 12, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
|
|
; CHECK-NEXT: # fallthrough-return
|
|
entry:
|
|
%0 = trunc <4 x i32> %a to <4 x i8>
|
|
ret <4 x i8> %0
|
|
}
|