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
140 lines
9.3 KiB
LLVM
140 lines
9.3 KiB
LLVM
; RUN: opt -passes=verify --disable-output %s
|
|
|
|
define void @test_vp_int(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n) {
|
|
%r0 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r1 = call <8 x i32> @llvm.vp.sub.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r2 = call <8 x i32> @llvm.vp.mul.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r3 = call <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r7 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r8 = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%r9 = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%rA = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%rB = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
%rC = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
|
|
ret void
|
|
}
|
|
|
|
|
|
define void @test_vp_fp(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n) {
|
|
%r0 = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
|
|
%r1 = call <8 x double> @llvm.vp.fsub.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
|
|
%r2 = call <8 x double> @llvm.vp.fmul.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
|
|
%r3 = call <8 x double> @llvm.vp.fdiv.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
|
|
%r4 = call <8 x double> @llvm.vp.frem.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
|
|
%r5 = call <8 x i1> @llvm.vp.is.fpclass.v8f64(<8 x double> %f0, i32 639, <8 x i1> %m, i32 %n)
|
|
ret void
|
|
}
|
|
|
|
; TODO: test_vp_constrained_fp
|
|
|
|
|
|
define void @test_vp_reduction(i32 %x, <8 x i32> %vi, <8 x float> %vf, float %f, <8 x i1> %m, i32 %n) {
|
|
%r0 = call i32 @llvm.vp.reduce.add.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r1 = call i32 @llvm.vp.reduce.mul.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r2 = call i32 @llvm.vp.reduce.and.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r3 = call i32 @llvm.vp.reduce.or.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r4 = call i32 @llvm.vp.reduce.xor.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r5 = call i32 @llvm.vp.reduce.smax.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r6 = call i32 @llvm.vp.reduce.smin.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r7 = call i32 @llvm.vp.reduce.umax.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r8 = call i32 @llvm.vp.reduce.umin.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
|
|
%r9 = call float @llvm.vp.reduce.fmin.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
|
|
%rA = call float @llvm.vp.reduce.fmax.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
|
|
%rB = call float @llvm.vp.reduce.fminimum.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
|
|
%rC = call float @llvm.vp.reduce.fmaximum.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
|
|
%rD = call float @llvm.vp.reduce.fadd.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
|
|
%rE = call float @llvm.vp.reduce.fmul.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
|
|
ret void
|
|
}
|
|
|
|
define void @test_vp_splice0(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %l0, i32 %l1) {
|
|
%r0 = call <8 x i32> @llvm.experimental.vp.splice.v8i32(<8 x i32> %i0, <8 x i32> %i1, i32 2, <8 x i1> %m, i32 %l0, i32 %l1)
|
|
ret void
|
|
}
|
|
|
|
define void @test_vp_splice1(<vscale x 8 x i32> %i0, <vscale x 8 x i32> %i1, <vscale x 8 x i1> %m, i32 %l0, i32 %l1) {
|
|
%r0 = call <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32> %i0, <vscale x 8 x i32> %i1, i32 -1, <vscale x 8 x i1> %m, i32 %l0, i32 %l1)
|
|
ret void
|
|
}
|
|
|
|
define void @test_vp_conversions(<8 x ptr> %p0, <8 x i32> %i0, <8 x i64> %i1, <8 x float> %f0, <8 x double> %f1, <8 x i1> %mask, i32 %evl) {
|
|
%r0 = call <8 x i32> @llvm.vp.fptoui.v8i32.v8f32(<8 x float> %f0, <8 x i1> %mask, i32 %evl)
|
|
%r1 = call <8 x i32> @llvm.vp.fptosi.v8i32.v8f32(<8 x float> %f0, <8 x i1> %mask, i32 %evl)
|
|
%r2 = call <8 x float> @llvm.vp.uitofp.v8f32.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)
|
|
%r3 = call <8 x float> @llvm.vp.sitofp.v8f32.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)
|
|
%r4 = call <8 x float> @llvm.vp.fptrunc.v8f32.v8f64(<8 x double> %f1, <8 x i1> %mask, i32 %evl)
|
|
%r5 = call <8 x double> @llvm.vp.fpext.v8f64.v8f32(<8 x float> %f0, <8 x i1> %mask, i32 %evl)
|
|
%r6 = call <8 x i32> @llvm.vp.trunc.v8i32.v8i64(<8 x i64> %i1, <8 x i1> %mask, i32 %evl)
|
|
%r7 = call <8 x i64> @llvm.vp.zext.v8i64.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)
|
|
%r8 = call <8 x i64> @llvm.vp.sext.v8i64.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)
|
|
%r9 = call <8 x i32> @llvm.vp.ptrtoint.v8i32.v8p0(<8 x ptr> %p0, <8 x i1> %mask, i32 %evl)
|
|
%r10 = call <8 x ptr> @llvm.vp.inttoptr.v8p0.v8i32(<8 x i32> %i0, <8 x i1> %mask, i32 %evl)
|
|
ret void
|
|
}
|
|
|
|
define void @test_vp_comparisons(<8 x float> %f0, <8 x float> %f1, <8 x i32> %i0, <8 x i32> %i1, <8 x i1> %mask, i32 %evl) {
|
|
%r0 = call <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float> %f0, <8 x float> %f1, metadata !"oeq", <8 x i1> %mask, i32 %evl)
|
|
%r1 = call <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32> %i0, <8 x i32> %i1, metadata !"eq", <8 x i1> %mask, i32 %evl)
|
|
ret void
|
|
}
|
|
|
|
; integer arith
|
|
declare <8 x i32> @llvm.vp.add.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.sub.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.mul.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.srem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.urem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
; bit arith
|
|
declare <8 x i32> @llvm.vp.and.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.or.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.xor.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.shl.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
|
|
; fp arith
|
|
declare <8 x double> @llvm.vp.fadd.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
|
|
declare <8 x double> @llvm.vp.fsub.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
|
|
declare <8 x double> @llvm.vp.fmul.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
|
|
declare <8 x double> @llvm.vp.fdiv.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
|
|
declare <8 x double> @llvm.vp.frem.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
|
|
declare <8 x i1> @llvm.vp.is.fpclass.v8f64(<8 x double>, i32, <8 x i1>, i32)
|
|
; reductions
|
|
declare i32 @llvm.vp.reduce.add.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.mul.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.and.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.or.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.xor.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.smax.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.smin.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.umax.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare i32 @llvm.vp.reduce.umin.v8i32(i32, <8 x i32>, <8 x i1>, i32)
|
|
declare float @llvm.vp.reduce.fmin.v8f32(float, <8 x float>, <8 x i1>, i32)
|
|
declare float @llvm.vp.reduce.fmax.v8f32(float, <8 x float>, <8 x i1>, i32)
|
|
declare float @llvm.vp.reduce.fminimum.v8f32(float, <8 x float>, <8 x i1>, i32)
|
|
declare float @llvm.vp.reduce.fmaximum.v8f32(float, <8 x float>, <8 x i1>, i32)
|
|
declare float @llvm.vp.reduce.fadd.v8f32(float, <8 x float>, <8 x i1>, i32)
|
|
declare float @llvm.vp.reduce.fmul.v8f32(float, <8 x float>, <8 x i1>, i32)
|
|
; casts
|
|
declare <8 x i32> @llvm.vp.fptoui.v8i32.v8f32(<8 x float>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.fptosi.v8i32.v8f32(<8 x float>, <8 x i1>, i32)
|
|
declare <8 x float> @llvm.vp.uitofp.v8f32.v8i32(<8 x i32>, <8 x i1>, i32)
|
|
declare <8 x float> @llvm.vp.sitofp.v8f32.v8i32(<8 x i32>, <8 x i1>, i32)
|
|
declare <8 x float> @llvm.vp.fptrunc.v8f32.v8f64(<8 x double>, <8 x i1>, i32)
|
|
declare <8 x double> @llvm.vp.fpext.v8f64.v8f32(<8 x float>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.trunc.v8i32.v8i64(<8 x i64>, <8 x i1>, i32)
|
|
declare <8 x i64> @llvm.vp.zext.v8i64.v8i32(<8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i64> @llvm.vp.sext.v8i64.v8i32(<8 x i32>, <8 x i1>, i32)
|
|
declare <8 x i32> @llvm.vp.ptrtoint.v8i32.v8p0(<8 x ptr>, <8 x i1>, i32)
|
|
declare <8 x ptr> @llvm.vp.inttoptr.v8p0.v8i32(<8 x i32>, <8 x i1>, i32)
|
|
; compares
|
|
declare <8 x i1> @llvm.vp.fcmp.v8f32(<8 x float>, <8 x float>, metadata, <8 x i1>, i32)
|
|
declare <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32>, <8 x i32>, metadata, <8 x i1>, i32)
|
|
; shuffles
|
|
declare <8 x i32> @llvm.experimental.vp.splice.v8i32(<8 x i32>, <8 x i32>, i32, <8 x i1>, i32, i32)
|
|
declare <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>, i32, <vscale x 8 x i1>, i32, i32)
|