[mips][msa] Added support for matching bmnz, bmnzi, bmz, and bmzi from normal IR (i.e. not intrinsics)

Also corrected the definition of the intrinsics for these instructions (the
result register is also the first operand), and added intrinsics for bsel and
bseli to clang (they already existed in the backend).

These four operations are mostly equivalent to bsel, and bseli (the difference
is which operand is tied to the result). As a result some of the tests changed
as described below.

bitwise.ll:
- bsel.v test adapted so that the mask is unknown at compile-time. This stops
  it emitting bmnzi.b instead of the intended bsel.v.
- The bseli.b test now tests the right thing. Namely the case when one of the
  values is an uimm8, rather than when the condition is a uimm8 (which is
  covered by bmnzi.b)

compare.ll:
- bsel.v tests now (correctly) emits bmnz.v instead of bsel.v because this
  is the same operation (see MSA.txt).

i8.ll
- CHECK-DAG-ized test.
- bmzi.b test now (correctly) emits equivalent bmnzi.b with swapped operands
  because this is the same operation (see MSA.txt).
- bseli.b still emits bseli.b though because the immediate makes it
  distinguishable from bmnzi.b.

vec.ll:
- CHECK-DAG-ized test.
- bmz.v tests now (correctly) emits bmnz.v with swapped operands (see
  MSA.txt).
- bsel.v tests now (correctly) emits bmnz.v with swapped operands (see
  MSA.txt).

llvm-svn: 193693

1 files changed, 17 insertions, 10 deletions

diff --git a/clang/test/CodeGen/builtins-mips-msa.c b/clang/test/CodeGen/builtins-mips-msa.c
index 47e16b790a5..da78a6df25b 100644
--- a/clang/test/CodeGen/builtins-mips-msa.c
+++ b/clang/test/CodeGen/builtins-mips-msa.c
@@ -170,19 +170,19 @@ void test(void) {
   v4i32_r = __builtin_msa_binsri_w(v4i32_r, v4i32_a, 25); // CHECK: call <4  x i32> @llvm.mips.binsri.w(
   v2i64_r = __builtin_msa_binsri_d(v2i64_r, v2i64_a, 25); // CHECK: call <2  x i64> @llvm.mips.binsri.d(
 
-  v16i8_r = __builtin_msa_bmnz_v(v16i8_a, v16i8_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
-  v8i16_r = __builtin_msa_bmnz_v(v8i16_a, v8i16_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
-  v4i32_r = __builtin_msa_bmnz_v(v4i32_a, v4i32_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
-  v2i64_r = __builtin_msa_bmnz_v(v2i64_a, v2i64_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
+  v16i8_r = __builtin_msa_bmnz_v(v16i8_r, v16i8_a, v16i8_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
+  v8i16_r = __builtin_msa_bmnz_v(v8i16_r, v8i16_a, v8i16_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
+  v4i32_r = __builtin_msa_bmnz_v(v4i32_r, v4i32_a, v4i32_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
+  v2i64_r = __builtin_msa_bmnz_v(v2i64_r, v2i64_a, v2i64_b); // CHECK: call <16 x i8> @llvm.mips.bmnz.v(
 
-  v16i8_r = __builtin_msa_bmnzi_b(v16i8_a, 25); // CHECK: call <16 x i8>  @llvm.mips.bmnzi.b(
+  v16i8_r = __builtin_msa_bmnzi_b(v16i8_r, v16i8_a, 25); // CHECK: call <16 x i8>  @llvm.mips.bmnzi.b(
 
-  v16i8_r = __builtin_msa_bmz_v(v16i8_a, v16i8_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
-  v8i16_r = __builtin_msa_bmz_v(v8i16_a, v8i16_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
-  v4i32_r = __builtin_msa_bmz_v(v4i32_a, v4i32_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
-  v2i64_r = __builtin_msa_bmz_v(v2i64_a, v2i64_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
+  v16i8_r = __builtin_msa_bmz_v(v16i8_r, v16i8_a, v16i8_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
+  v8i16_r = __builtin_msa_bmz_v(v8i16_r, v8i16_a, v8i16_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
+  v4i32_r = __builtin_msa_bmz_v(v4i32_r, v4i32_a, v4i32_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
+  v2i64_r = __builtin_msa_bmz_v(v2i64_r, v2i64_a, v2i64_b); // CHECK: call <16 x i8> @llvm.mips.bmz.v(
 
-  v16i8_r = __builtin_msa_bmzi_b(v16i8_a, 25); // CHECK: call <16 x i8>  @llvm.mips.bmzi.b(
+  v16i8_r = __builtin_msa_bmzi_b(v16i8_r, v16i8_a, 25); // CHECK: call <16 x i8>  @llvm.mips.bmzi.b(
 
   v16i8_r = __builtin_msa_bneg_b(v16i8_a, v16i8_b); // CHECK: call <16 x i8>  @llvm.mips.bneg.b(
   v8i16_r = __builtin_msa_bneg_h(v8i16_a, v8i16_b); // CHECK: call <8  x i16> @llvm.mips.bneg.h(
@@ -201,6 +201,13 @@ void test(void) {
 
   int_r = __builtin_msa_bnz_v(v16i8_a); // CHECK: call i32 @llvm.mips.bnz.v(
 
+  v16i8_r = __builtin_msa_bsel_v(v16i8_r, v16i8_a, v16i8_b); // CHECK: call <16 x i8> @llvm.mips.bsel.v(
+  v8i16_r = __builtin_msa_bsel_v(v8i16_r, v8i16_a, v8i16_b); // CHECK: call <16 x i8> @llvm.mips.bsel.v(
+  v4i32_r = __builtin_msa_bsel_v(v4i32_r, v4i32_a, v4i32_b); // CHECK: call <16 x i8> @llvm.mips.bsel.v(
+  v2i64_r = __builtin_msa_bsel_v(v2i64_r, v2i64_a, v2i64_b); // CHECK: call <16 x i8> @llvm.mips.bsel.v(
+
+  v16i8_r = __builtin_msa_bseli_b(v16i8_r, v16i8_a, 25); // CHECK: call <16 x i8>  @llvm.mips.bseli.b(
+
   v16i8_r = __builtin_msa_bset_b(v16i8_a, v16i8_b); // CHECK: call <16 x i8>  @llvm.mips.bset.b(
   v8i16_r = __builtin_msa_bset_h(v8i16_a, v8i16_b); // CHECK: call <8  x i16> @llvm.mips.bset.h(
   v4i32_r = __builtin_msa_bset_w(v4i32_a, v4i32_b); // CHECK: call <4  x i32> @llvm.mips.bset.w(