From 32cfa5ba839a9b54f53519108c1a45fb4d046ef4 Mon Sep 17 00:00:00 2001 From: Simon Pilgrim Date: Wed, 7 Sep 2016 14:49:50 +0000 Subject: [PATCH] [X86][SSE] Added or combine tests for known bits of vectors Part of the yak shaving for D24253 llvm-svn: 280813 --- llvm/test/CodeGen/X86/combine-or.ll | 51 +++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) diff --git a/llvm/test/CodeGen/X86/combine-or.ll b/llvm/test/CodeGen/X86/combine-or.ll index 5cbd749..143c403 100644 --- a/llvm/test/CodeGen/X86/combine-or.ll +++ b/llvm/test/CodeGen/X86/combine-or.ll @@ -415,3 +415,54 @@ define <4 x i32> @test2f(<4 x i32> %a, <4 x i32> %b) { %or = or <4 x i32> %shuf1, %shuf2 ret <4 x i32> %or } + +; (or (and X, c1), c2) -> (and (or X, c2), c1|c2) + +define <2 x i64> @or_and_v2i64(<2 x i64> %a0) { +; CHECK-LABEL: or_and_v2i64: +; CHECK: # BB#0: +; CHECK-NEXT: andps {{.*}}(%rip), %xmm0 +; CHECK-NEXT: orps {{.*}}(%rip), %xmm0 +; CHECK-NEXT: retq + %1 = and <2 x i64> %a0, + %2 = or <2 x i64> %1, + ret <2 x i64> %2 +} + +define <4 x i32> @or_and_v4i32(<4 x i32> %a0) { +; CHECK-LABEL: or_and_v4i32: +; CHECK: # BB#0: +; CHECK-NEXT: andps {{.*}}(%rip), %xmm0 +; CHECK-NEXT: orps {{.*}}(%rip), %xmm0 +; CHECK-NEXT: retq + %1 = and <4 x i32> %a0, + %2 = or <4 x i32> %1, + ret <4 x i32> %2 +} + +; fold (or x, c) -> c iff (x & ~c) == 0 + +define <2 x i64> @or_zext_v2i32(<2 x i32> %a0) { +; CHECK-LABEL: or_zext_v2i32: +; CHECK: # BB#0: +; CHECK-NEXT: pxor %xmm1, %xmm1 +; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7] +; CHECK-NEXT: por {{.*}}(%rip), %xmm0 +; CHECK-NEXT: retq + %1 = zext <2 x i32> %a0 to <2 x i64> + %2 = or <2 x i64> %1, + ret <2 x i64> %2 +} + +define <4 x i32> @or_zext_v4i16(<4 x i16> %a0) { +; CHECK-LABEL: or_zext_v4i16: +; CHECK: # BB#0: +; CHECK-NEXT: pxor %xmm1, %xmm1 +; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7] +; CHECK-NEXT: por {{.*}}(%rip), %xmm0 +; CHECK-NEXT: retq + %1 = zext <4 x i16> %a0 to <4 x i32> + %2 = or <4 x i32> %1, + ret <4 x i32> %2 +} + -- 2.7.4