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
160 lines
7.7 KiB
LLVM
160 lines
7.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx,+f16c -show-mc-encoding -disable-peephole | FileCheck %s --check-prefixes=AVX,X86
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+f16c -show-mc-encoding -disable-peephole | FileCheck %s --check-prefixes=AVX,X64
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512vl -show-mc-encoding -disable-peephole | FileCheck %s --check-prefixes=AVX512VL,X86-AVX512VL
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl -show-mc-encoding -disable-peephole | FileCheck %s --check-prefixes=AVX512VL,X64-AVX512VL
|
|
|
|
define <8 x i16> @test_x86_vcvtps2ph_128(<4 x float> %a0) {
|
|
; AVX-LABEL: test_x86_vcvtps2ph_128:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vcvtps2ph $0, %xmm0, %xmm0 # encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x00]
|
|
; AVX-NEXT: ret{{[l|q]}} # encoding: [0xc3]
|
|
;
|
|
; AVX512VL-LABEL: test_x86_vcvtps2ph_128:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vcvtps2ph $0, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0xc0,0x00]
|
|
; AVX512VL-NEXT: ret{{[l|q]}} # encoding: [0xc3]
|
|
%res = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float>, i32) nounwind readonly
|
|
|
|
define <8 x i16> @test_x86_vcvtps2ph_256(<8 x float> %a0) {
|
|
; AVX-LABEL: test_x86_vcvtps2ph_256:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vcvtps2ph $0, %ymm0, %xmm0 # encoding: [0xc4,0xe3,0x7d,0x1d,0xc0,0x00]
|
|
; AVX-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
|
|
; AVX-NEXT: ret{{[l|q]}} # encoding: [0xc3]
|
|
;
|
|
; AVX512VL-LABEL: test_x86_vcvtps2ph_256:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vcvtps2ph $0, %ymm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x1d,0xc0,0x00]
|
|
; AVX512VL-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
|
|
; AVX512VL-NEXT: ret{{[l|q]}} # encoding: [0xc3]
|
|
%res = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float>, i32) nounwind readonly
|
|
|
|
|
|
define void @test_x86_vcvtps2ph_256_m(ptr nocapture %d, <8 x float> %a) nounwind {
|
|
; X86-LABEL: test_x86_vcvtps2ph_256_m:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-NEXT: vcvtps2ph $3, %ymm0, (%eax) # encoding: [0xc4,0xe3,0x7d,0x1d,0x00,0x03]
|
|
; X86-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
|
|
; X86-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-LABEL: test_x86_vcvtps2ph_256_m:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vcvtps2ph $3, %ymm0, (%rdi) # encoding: [0xc4,0xe3,0x7d,0x1d,0x07,0x03]
|
|
; X64-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
|
|
; X64-NEXT: retq # encoding: [0xc3]
|
|
;
|
|
; X86-AVX512VL-LABEL: test_x86_vcvtps2ph_256_m:
|
|
; X86-AVX512VL: # %bb.0: # %entry
|
|
; X86-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-AVX512VL-NEXT: vcvtps2ph $3, %ymm0, (%eax) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x1d,0x00,0x03]
|
|
; X86-AVX512VL-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
|
|
; X86-AVX512VL-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_256_m:
|
|
; X64-AVX512VL: # %bb.0: # %entry
|
|
; X64-AVX512VL-NEXT: vcvtps2ph $3, %ymm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x7d,0x1d,0x07,0x03]
|
|
; X64-AVX512VL-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
|
|
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a, i32 3)
|
|
store <8 x i16> %0, ptr %d, align 16
|
|
ret void
|
|
}
|
|
|
|
define void @test_x86_vcvtps2ph_128_m(ptr nocapture %d, <4 x float> %a) nounwind {
|
|
; X86-LABEL: test_x86_vcvtps2ph_128_m:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-NEXT: vcvtps2ph $3, %xmm0, (%eax) # encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
|
|
; X86-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-LABEL: test_x86_vcvtps2ph_128_m:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
|
|
; X64-NEXT: retq # encoding: [0xc3]
|
|
;
|
|
; X86-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m:
|
|
; X86-AVX512VL: # %bb.0: # %entry
|
|
; X86-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%eax) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
|
|
; X86-AVX512VL-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m:
|
|
; X64-AVX512VL: # %bb.0: # %entry
|
|
; X64-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
|
|
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a, i32 3)
|
|
%1 = shufflevector <8 x i16> %0, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
store <4 x i16> %1, ptr %d, align 8
|
|
ret void
|
|
}
|
|
|
|
define void @test_x86_vcvtps2ph_128_m2(ptr nocapture %hf4x16, <4 x float> %f4X86) #0 {
|
|
; X86-LABEL: test_x86_vcvtps2ph_128_m2:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-NEXT: vcvtps2ph $3, %xmm0, (%eax) # encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
|
|
; X86-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-LABEL: test_x86_vcvtps2ph_128_m2:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
|
|
; X64-NEXT: retq # encoding: [0xc3]
|
|
;
|
|
; X86-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m2:
|
|
; X86-AVX512VL: # %bb.0: # %entry
|
|
; X86-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%eax) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
|
|
; X86-AVX512VL-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m2:
|
|
; X64-AVX512VL: # %bb.0: # %entry
|
|
; X64-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
|
|
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4X86, i32 3)
|
|
%1 = bitcast <8 x i16> %0 to <2 x double>
|
|
%vecext = extractelement <2 x double> %1, i32 0
|
|
store double %vecext, ptr %hf4x16, align 8
|
|
ret void
|
|
}
|
|
|
|
define void @test_x86_vcvtps2ph_128_m3(ptr nocapture %hf4x16, <4 x float> %f4X86) #0 {
|
|
; X86-LABEL: test_x86_vcvtps2ph_128_m3:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-NEXT: vcvtps2ph $3, %xmm0, (%eax) # encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
|
|
; X86-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-LABEL: test_x86_vcvtps2ph_128_m3:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
|
|
; X64-NEXT: retq # encoding: [0xc3]
|
|
;
|
|
; X86-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m3:
|
|
; X86-AVX512VL: # %bb.0: # %entry
|
|
; X86-AVX512VL-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
|
|
; X86-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%eax) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x00,0x03]
|
|
; X86-AVX512VL-NEXT: retl # encoding: [0xc3]
|
|
;
|
|
; X64-AVX512VL-LABEL: test_x86_vcvtps2ph_128_m3:
|
|
; X64-AVX512VL: # %bb.0: # %entry
|
|
; X64-AVX512VL-NEXT: vcvtps2ph $3, %xmm0, (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe3,0x79,0x1d,0x07,0x03]
|
|
; X64-AVX512VL-NEXT: retq # encoding: [0xc3]
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4X86, i32 3)
|
|
%1 = bitcast <8 x i16> %0 to <2 x i64>
|
|
%vecext = extractelement <2 x i64> %1, i32 0
|
|
store i64 %vecext, ptr %hf4x16, align 8
|
|
ret void
|
|
}
|