[SystemZ] Bugfix in SystemZVectorConstantInfo

In order to correctly load an all-ones FP NaN value into a floating point
register with a VGBM, the analyzed 32/64 FP bits must first be shifted left
(into element 0 of the vector register).

SystemZVectorConstantInfo has so far relied on element replication which has
bypassed the need to do this shift, but now it is clear that this must be
done in order to handle NaNs.

Review: Ulrich Weigand

Differential Revision: https://reviews.llvm.org/D89389

diff --git a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
index 9f18058..27fdf39 100644 (file)
--- a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
@@ -784,10 +784,11 @@ bool SystemZVectorConstantInfo::isVectorConstantLegal(
 SystemZVectorConstantInfo::SystemZVectorConstantInfo(APFloat FPImm) {
   IntBits = FPImm.bitcastToAPInt().zextOrSelf(128);
   isFP128 = (&FPImm.getSemantics() == &APFloat::IEEEquad());
-
-  // Find the smallest splat.
   SplatBits = FPImm.bitcastToAPInt();
   unsigned Width = SplatBits.getBitWidth();
+  IntBits <<= (SystemZ::VectorBits - Width);
+
+  // Find the smallest splat.
   while (Width > 8) {
     unsigned HalfSize = Width / 2;
     APInt HighValue = SplatBits.lshr(HalfSize).trunc(HalfSize);

diff --git a/llvm/test/CodeGen/SystemZ/fp-const-12.ll b/llvm/test/CodeGen/SystemZ/fp-const-12.ll
index f22156b..89a3964 100644 (file)
--- a/llvm/test/CodeGen/SystemZ/fp-const-12.ll
+++ b/llvm/test/CodeGen/SystemZ/fp-const-12.ll
@@ -1,4 +1,4 @@
-; Test loads of FP constants with VGM.
+; Test loads of FP constants with VGM and VGBM.
 ;
 ; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
 
@@ -61,3 +61,15 @@ define float @f10() {
 ; CHECK: vgmf %v0, 2, 6
   ret float 0.125
 }
+
+define float @f11() {
+; CHECK-LABEL: f11:
+; CHECK: vgbm %v0, 61440
+  ret float 0xFFFFFFFFE0000000
+}
+
+define double @f12() {
+; CHECK-LABEL: f12:
+; CHECK: vgbm %v0, 61440
+  ret double 0xFFFFFFFF00000000
+}

diff --git a/llvm/test/CodeGen/SystemZ/vector-constrained-fp-intrinsics.ll b/llvm/test/CodeGen/SystemZ/vector-constrained-fp-intrinsics.ll
index b7cbac8..8752e6b 100644 (file)
--- a/llvm/test/CodeGen/SystemZ/vector-constrained-fp-intrinsics.ll
+++ b/llvm/test/CodeGen/SystemZ/vector-constrained-fp-intrinsics.ll
@@ -802,7 +802,7 @@ define <3 x float> @constrained_vector_fadd_v3f32() #0 {
 ;
 ; SZ13-LABEL: constrained_vector_fadd_v3f32:
 ; SZ13:       # %bb.0: # %entry
-; SZ13-NEXT:    vgbm %v0, 15
+; SZ13-NEXT:    vgbm %v0, 61440
 ; SZ13-NEXT:    vgmf %v2, 1, 1
 ; SZ13-NEXT:    vgmf %v3, 2, 8
 ; SZ13-NEXT:    lzer %f1
@@ -974,12 +974,12 @@ define <3 x float> @constrained_vector_fsub_v3f32() #0 {
 ;
 ; SZ13-LABEL: constrained_vector_fsub_v3f32:
 ; SZ13:       # %bb.0: # %entry
-; SZ13-NEXT:    vgbm %v2, 15
+; SZ13-NEXT:    vgbm %v2, 61440
 ; SZ13-NEXT:    lzer %f1
 ; SZ13-NEXT:    sebr %f2, %f1
 ; SZ13-NEXT:    vgmf %v1, 1, 1
-; SZ13-NEXT:    vgbm %v3, 15
-; SZ13-NEXT:    vgbm %v0, 15
+; SZ13-NEXT:    vgbm %v3, 61440
+; SZ13-NEXT:    vgbm %v0, 61440
 ; SZ13-NEXT:    sebr %f3, %f1
 ; SZ13-NEXT:    vgmf %v1, 2, 8
 ; SZ13-NEXT:    sebr %f0, %f1