From 468bf732096c813a76fbad0ab204b0cf7269f82a Mon Sep 17 00:00:00 2001
From: Justin Lebar <jlebar@google.com>
Date: Fri, 28 Oct 2016 21:43:51 +0000
Subject: [PATCH] Don't claim the udiv created in BypassSlowDivision is exact.

Summary:
In BypassSlowDivision's short-dividend path, we would create e.g.

  udiv exact i32 %a, %b

"exact" here means that we are asserting that %a is a multiple of %b.
But we have no reason to believe this must be true -- this is just a
bug, as far as I can tell.

Reviewers: tra

Subscribers: jholewinski, llvm-commits

Differential Revision: https://reviews.llvm.org/D26097

llvm-svn: 285459
---
 llvm/lib/Transforms/Utils/BypassSlowDivision.cpp |  3 +--
 .../NVPTX/bypass-slow-div-not-exact.ll           | 16 ++++++++++++++++
 2 files changed, 17 insertions(+), 2 deletions(-)
 create mode 100644 llvm/test/Transforms/CodeGenPrepare/NVPTX/bypass-slow-div-not-exact.ll

diff --git a/llvm/lib/Transforms/Utils/BypassSlowDivision.cpp b/llvm/lib/Transforms/Utils/BypassSlowDivision.cpp
index 42287d3bb2e8..41a854362c92 100644
--- a/llvm/lib/Transforms/Utils/BypassSlowDivision.cpp
+++ b/llvm/lib/Transforms/Utils/BypassSlowDivision.cpp
@@ -120,8 +120,7 @@ static bool insertFastDiv(Instruction *I, IntegerType *BypassType,
                                                  BypassType);
 
   // udiv/urem because optimization only handles positive numbers
-  Value *ShortQuotientV = FastBuilder.CreateExactUDiv(ShortDividendV,
-                                                      ShortDivisorV);
+  Value *ShortQuotientV = FastBuilder.CreateUDiv(ShortDividendV, ShortDivisorV);
   Value *ShortRemainderV = FastBuilder.CreateURem(ShortDividendV,
                                                   ShortDivisorV);
   Value *FastQuotientV = FastBuilder.CreateCast(Instruction::ZExt,
diff --git a/llvm/test/Transforms/CodeGenPrepare/NVPTX/bypass-slow-div-not-exact.ll b/llvm/test/Transforms/CodeGenPrepare/NVPTX/bypass-slow-div-not-exact.ll
new file mode 100644
index 000000000000..9db23d639a4c
--- /dev/null
+++ b/llvm/test/Transforms/CodeGenPrepare/NVPTX/bypass-slow-div-not-exact.ll
@@ -0,0 +1,16 @@
+; RUN: opt -S -codegenprepare < %s | FileCheck %s
+
+target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+; Check that the smaller-width division that the BypassSlowDivision pass
+; creates is not marked as "exact" (that is, it doesn't claim that the
+; numerator is a multiple of the denominator).
+;
+; CHECK-LABEL: @test
+define void @test(i64 %a, i64 %b, i64* %retptr) {
+  ; CHECK: udiv i32
+  %d = sdiv i64 %a, %b
+  store i64 %d, i64* %retptr
+  ret void
+}