From 1045928aab8d33bcef57e004ebdd5482468922e6 Mon Sep 17 00:00:00 2001 From: Nicolai Haehnle Date: Thu, 21 Jun 2018 13:37:19 +0000 Subject: AMDGPU: Convert test cases to the dimension-aware intrinsics Summary: Also explicitly port over some tests in llvm.amdgcn.image.* that were missing. Some tests are removed because they no longer apply (i.e. explicitly testing building an address vector via insertelement). This is in preparation for the eventual removal of the old-style intrinsics. Some additional notes: - constant-address-space-32bit.ll: change some GCN-NEXT to GCN because the instruction schedule was subtly altered - insert_vector_elt.ll: the old test didn't actually test anything, because %tmp1 was not used; remove the load, because it doesn't work (Because of the amdgpu_ps calling convention? In any case, it's orthogonal to what the test claims to be testing.) Change-Id: Idfa99b6512ad139e755e82b8b89548ab08f0afcf Reviewers: arsenm, rampitec Subscribers: MatzeB, qcolombet, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D48018 llvm-svn: 335229 --- llvm/test/CodeGen/AMDGPU/split-smrd.ll | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'llvm/test/CodeGen/AMDGPU/split-smrd.ll') diff --git a/llvm/test/CodeGen/AMDGPU/split-smrd.ll b/llvm/test/CodeGen/AMDGPU/split-smrd.ll index 6089492b1c2..46355b762b4 100644 --- a/llvm/test/CodeGen/AMDGPU/split-smrd.ll +++ b/llvm/test/CodeGen/AMDGPU/split-smrd.ll @@ -21,7 +21,7 @@ bb3: ; preds = %bb %tmp6 = sext i32 %tmp5 to i64 %tmp7 = getelementptr [34 x <8 x i32>], [34 x <8 x i32>] addrspace(4)* %arg, i64 0, i64 %tmp6 %tmp8 = load <8 x i32>, <8 x i32> addrspace(4)* %tmp7, align 32, !tbaa !0 - %tmp9 = call <4 x float> @llvm.amdgcn.image.sample.v4f32.v2f32.v8i32(<2 x float> , <8 x i32> %tmp8, <4 x i32> undef, i32 15, i1 false, i1 false, i1 false, i1 false, i1 false) + %tmp9 = call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 15, float bitcast (i32 1061158912 to float), float bitcast (i32 1048576000 to float), <8 x i32> %tmp8, <4 x i32> undef, i1 0, i32 0, i32 0) %tmp10 = extractelement <4 x float> %tmp9, i32 0 %tmp12 = call <2 x half> @llvm.amdgcn.cvt.pkrtz(float %tmp10, float undef) call void @llvm.amdgcn.exp.compr.v2f16(i32 0, i32 15, <2 x half> %tmp12, <2 x half> undef, i1 true, i1 true) #0 @@ -30,7 +30,7 @@ bb3: ; preds = %bb declare <2 x half> @llvm.amdgcn.cvt.pkrtz(float, float) #1 declare void @llvm.amdgcn.exp.compr.v2f16(i32, i32, <2 x half>, <2 x half>, i1, i1) #0 -declare <4 x float> @llvm.amdgcn.image.sample.v4f32.v2f32.v8i32(<2 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #2 +declare <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #2 declare float @llvm.SI.load.const.v4i32(<4 x i32>, i32) #1 attributes #0 = { nounwind } -- cgit v1.2.3