llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clang-codegen Author: None (RolandF77) <details> <summary>Changes</summary> Add support for PPC Dense Math basic builtins dmsetdmrz, dmmr, dmxor. --- Full diff: https://github.com/llvm/llvm-project/pull/145372.diff 3 Files Affected: - (modified) clang/include/clang/Basic/BuiltinsPPC.def (+6) - (modified) clang/lib/CodeGen/TargetBuiltins/PPC.cpp (+5) - (modified) clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c (+16) ``````````diff diff --git a/clang/include/clang/Basic/BuiltinsPPC.def b/clang/include/clang/Basic/BuiltinsPPC.def index 099500754a0e0..7f4dc9fe4f719 100644 --- a/clang/include/clang/Basic/BuiltinsPPC.def +++ b/clang/include/clang/Basic/BuiltinsPPC.def @@ -1146,6 +1146,12 @@ UNALIASED_CUSTOM_BUILTIN(mma_dmxvi8gerx4spp, "vW1024*W256V", true, "mma,paired-vector-memops") UNALIASED_CUSTOM_BUILTIN(mma_pmdmxvi8gerx4spp, "vW1024*W256Vi255i15i15", true, "mma,paired-vector-memops") +UNALIASED_CUSTOM_BUILTIN(mma_dmsetdmrz, "vW1024*", false, + "mma,paired-vector-memops") +UNALIASED_CUSTOM_BUILTIN(mma_dmmr, "vW1024*W1024*", false, + "mma,paired-vector-memops") +UNALIASED_CUSTOM_BUILTIN(mma_dmxor, "vW1024*W1024*", true, + "mma,paired-vector-memops") // FIXME: Obviously incomplete. diff --git a/clang/lib/CodeGen/TargetBuiltins/PPC.cpp b/clang/lib/CodeGen/TargetBuiltins/PPC.cpp index f9890285f0aab..270e9fc976f23 100644 --- a/clang/lib/CodeGen/TargetBuiltins/PPC.cpp +++ b/clang/lib/CodeGen/TargetBuiltins/PPC.cpp @@ -1151,6 +1151,11 @@ Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID, Value *Acc = Builder.CreateLoad(Addr); CallOps.push_back(Acc); } + if (BuiltinID == PPC::BI__builtin_mma_dmmr || + BuiltinID == PPC::BI__builtin_mma_dmxor) { + Address Addr = EmitPointerWithAlignment(E->getArg(1)); + Ops[1] = Builder.CreateLoad(Addr); + } for (unsigned i=1; i<Ops.size(); i++) CallOps.push_back(Ops[i]); llvm::Function *F = CGM.getIntrinsic(ID); diff --git a/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c b/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c index 41f13155847ba..4aafc09602228 100644 --- a/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c +++ b/clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c @@ -92,3 +92,19 @@ void test_pmdmxvi8gerx4spp(unsigned char *vdmrp, unsigned char *vpp, vector unsi __builtin_mma_pmdmxvi8gerx4spp(&vdmr, vp, vc, 0, 0, 0); *((__dmr1024 *)resp) = vdmr; } + +// CHECK-LABEL: @test_dmf_basic +// CHECK-NEXT: entry: +// CHECK-NEXT: [[TMP0:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmsetdmrz() +// CHECK-NEXT: [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmmr(<1024 x i1> [[TMP0]]) +// CHECK-NEXT: store <1024 x i1> [[TMP1]], ptr %res1, align 128 +// CHECK-NEXT: [[TMP2:%.*]] = load <1024 x i1>, ptr %res2, align 128 +// CHECK-NEXT: [[TMP3:%.*]] = load <1024 x i1>, ptr %p, align 128 +// CHECK-NEXT: [[TMP4:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxor(<1024 x i1> [[TMP2]], <1024 x i1> [[TMP3]]) +// CHECK-NEXT: store <1024 x i1> [[TMP4]], ptr %res2, align 128 +void test_dmf_basic(char *p, char *res1, char *res2) { + __dmr1024 x[2]; + __builtin_mma_dmsetdmrz(&x[0]); + __builtin_mma_dmmr((__dmr1024*)res1, &x[0]); + __builtin_mma_dmxor((__dmr1024*)res2, (__dmr1024*)p); +} `````````` </details> https://github.com/llvm/llvm-project/pull/145372 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
