Index: llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp =================================================================== --- llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp +++ llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp @@ -1239,6 +1239,12 @@ if (EltVT.isVector()) { NumElts = EltVT.getVectorNumElements(); EltVT = EltVT.getVectorElementType(); + // vectors of f16 are loaded/stored as multiples of v2f16 elements. + if (EltVT == MVT::f16 && N->getValueType(0) == MVT::v2f16 && + NumElts % 2 == 0) { + EltVT = MVT::v2f16; + NumElts /= 2; + } } // Build the "promoted" result VTList for the load. If we are really loading Index: llvm/test/CodeGen/NVPTX/ldg-invariant.ll =================================================================== --- llvm/test/CodeGen/NVPTX/ldg-invariant.ll +++ llvm/test/CodeGen/NVPTX/ldg-invariant.ll @@ -10,6 +10,51 @@ ret i32 %a } +; CHECK-LABEL: @ld_global_v2f16 +define half @ld_global_v2f16(<2 x half> addrspace(1)* %ptr) { +; Load of v2f16 is weird. We consider it to be a legal type, which happens to be +; loaded/stored as a 32-bit scalar. +; CHECK: ld.global.nc.b32 + %a = load <2 x half>, <2 x half> addrspace(1)* %ptr, !invariant.load !0 + %v1 = extractelement <2 x half> %a, i32 0 + %v2 = extractelement <2 x half> %a, i32 1 + %sum = fadd half %v1, %v2 + ret half %sum +} + +; CHECK-LABEL: @ld_global_v4f16 +define half @ld_global_v4f16(<4 x half> addrspace(1)* %ptr) { +; Larger f16 vectors may be split into individual f16 elements and multiple +; loads/stores may be vectorized using f16 element type. Practically it's +; limited to v4 variant only. +; CHECK: ld.global.nc.v4.b16 + %a = load <4 x half>, <4 x half> addrspace(1)* %ptr, !invariant.load !0 + %v1 = extractelement <4 x half> %a, i32 0 + %v2 = extractelement <4 x half> %a, i32 1 + %v3 = extractelement <4 x half> %a, i32 2 + %v4 = extractelement <4 x half> %a, i32 3 + %sum1 = fadd half %v1, %v2 + %sum2 = fadd half %v3, %v4 + %sum = fadd half %sum1, %sum2 + ret half %sum +} + +; CHECK-LABEL: @ld_global_v8f16 +define half @ld_global_v8f16(<8 x half> addrspace(1)* %ptr) { +; Larger vectors are, again, loaded as v4i32. PTX has no v8 variants of loads/stores, +; so load/store vectorizer has to convert v8f16 -> v4 x v2f16. +; CHECK: ld.global.nc.v4.b32 + %a = load <8 x half>, <8 x half> addrspace(1)* %ptr, !invariant.load !0 + %v1 = extractelement <8 x half> %a, i32 0 + %v2 = extractelement <8 x half> %a, i32 2 + %v3 = extractelement <8 x half> %a, i32 4 + %v8 = extractelement <8 x half> %a, i32 6 + %sum1 = fadd half %v1, %v2 + %sum2 = fadd half %v3, %v8 + %sum = fadd half %sum1, %sum2 + ret half %sum +} + ; CHECK-LABEL: @ld_global_v2i32 define i32 @ld_global_v2i32(<2 x i32> addrspace(1)* %ptr) { ; CHECK: ld.global.nc.v2.{{[a-z]}}32