[AMDGPU] Expand vector mulhu/mulhs

Differential revision: https://reviews.llvm.org/D26077

llvm-svn: 285684

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
index a7fd748..a69d1af 100644 (file)
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -359,6 +359,8 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(const TargetMachine &TM,
     setOperationAction(ISD::FP_TO_SINT, VT, Expand);
     setOperationAction(ISD::FP_TO_UINT, VT, Expand);
     setOperationAction(ISD::MUL,  VT, Expand);
+    setOperationAction(ISD::MULHU, VT, Expand);
+    setOperationAction(ISD::MULHS, VT, Expand);
     setOperationAction(ISD::OR,   VT, Expand);
     setOperationAction(ISD::SHL,  VT, Expand);
     setOperationAction(ISD::SRA,  VT, Expand);

diff --git a/llvm/test/CodeGen/AMDGPU/sdiv.ll b/llvm/test/CodeGen/AMDGPU/sdiv.ll
index 29d8934..66caad4 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/sdiv.ll
+++ b/llvm/test/CodeGen/AMDGPU/sdiv.ll
@@ -156,3 +156,16 @@ define void @v_sdiv_i25(i32 addrspace(1)* %out, i25 addrspace(1)* %in) {
 ;   store i64 %result, i64 addrspace(1)* %out, align 8
 ;   ret void
 ; }
+
+; FUNC-LABEL: @scalarize_mulhs_4xi32
+; SI: v_mul_hi_i32
+; SI: v_mul_hi_i32
+; SI: v_mul_hi_i32
+; SI: v_mul_hi_i32
+
+define void @scalarize_mulhs_4xi32(<4 x i32> addrspace(1)* nocapture readonly %in, <4 x i32> addrspace(1)* nocapture %out) {
+  %1 = load <4 x i32>, <4 x i32> addrspace(1)* %in, align 16
+  %2 = sdiv <4 x i32> %1, <i32 53668, i32 53668, i32 53668, i32 53668>
+  store <4 x i32> %2, <4 x i32> addrspace(1)* %out, align 16
+  ret void
+}

diff --git a/llvm/test/CodeGen/AMDGPU/udiv.ll b/llvm/test/CodeGen/AMDGPU/udiv.ll
index f72c220..02383a9 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/udiv.ll
+++ b/llvm/test/CodeGen/AMDGPU/udiv.ll
@@ -145,3 +145,16 @@ define void @v_udiv_i24(i32 addrspace(1)* %out, i24 addrspace(1)* %in) {
   store i32 %result.ext, i32 addrspace(1)* %out
   ret void
 }
+
+; FUNC-LABEL: @scalarize_mulhu_4xi32
+; SI: v_mul_hi_u32
+; SI: v_mul_hi_u32
+; SI: v_mul_hi_u32
+; SI: v_mul_hi_u32
+
+define void @scalarize_mulhu_4xi32(<4 x i32> addrspace(1)* nocapture readonly %in, <4 x i32> addrspace(1)* nocapture %out) {
+  %1 = load <4 x i32>, <4 x i32> addrspace(1)* %in, align 16
+  %2 = udiv <4 x i32> %1, <i32 53668, i32 53668, i32 53668, i32 53668>
+  store <4 x i32> %2, <4 x i32> addrspace(1)* %out, align 16
+  ret void
+}