Index: lib/Target/X86/X86ISelLowering.cpp =================================================================== --- lib/Target/X86/X86ISelLowering.cpp +++ lib/Target/X86/X86ISelLowering.cpp @@ -25658,6 +25658,10 @@ if (Subtarget.hasAVX2() && (Bits == 32 || Bits == 64)) return false; + // AVX512BW has shifts such as vpsllvw. + if (Subtarget.hasBWI() && Bits == 16) + return false; + // Otherwise, it's significantly cheaper to shift by a scalar amount than by a // fully general vector. return true; Index: test/Transforms/CodeGenPrepare/X86/x86-shuffle-sink.ll =================================================================== --- test/Transforms/CodeGenPrepare/X86/x86-shuffle-sink.ll +++ test/Transforms/CodeGenPrepare/X86/x86-shuffle-sink.ll @@ -25,13 +25,27 @@ } define <8 x i16> @test_16bit(<8 x i16> %lhs, <8 x i16> %tmp, i1 %tst) { -; CHECK-LABEL: @test_16bit -; CHECK: if_true: -; CHECK-NOT: shufflevector - -; CHECK: if_false: -; CHECK: [[SPLAT:%[0-9a-zA-Z_]+]] = shufflevector -; CHECK: shl <8 x i16> %lhs, [[SPLAT]] +; CHECK-SSE2-LABEL: @test_16bit +; CHECK-SSE2: if_true: +; CHECK-SSE2-NOT: shufflevector +; CHECK-SSE2: if_false: +; CHECK-SSE2: [[SPLAT:%[0-9a-zA-Z_]+]] = shufflevector +; CHECK-SSE2: shl <8 x i16> %lhs, [[SPLAT]] + +; CHECK-AVX2-LABEL: @test_16bit +; CHECK-AVX2: if_true: +; CHECK-AVX2-NOT: shufflevector +; CHECK-AVX2: if_false: +; CHECK-AVX2: [[SPLAT:%[0-9a-zA-Z_]+]] = shufflevector +; CHECK-AVX2: shl <8 x i16> %lhs, [[SPLAT]] + +; CHECK-AVX512BW-LABEL: @test_16bit +; CHECK-AVX512BW: [[SPLAT:%[0-9a-zA-Z_]+]] = shufflevector +; CHECK-AVX512BW: if_true: +; CHECK-AVX512BW-NOT: shufflevector +; CHECK-AVX512BW: if_false: +; CHECK-AVX512BW-NOT: shufflevector +; CHECK-AVX512BW: shl <8 x i16> %lhs, [[SPLAT]] %mask = shufflevector <8 x i16> %tmp, <8 x i16> undef, <8 x i32> zeroinitializer br i1 %tst, label %if_true, label %if_false