diff options
author | Jingyue Wu <jingyue@google.com> | 2014-09-01 03:47:25 +0000 |
---|---|---|
committer | Jingyue Wu <jingyue@google.com> | 2014-09-01 03:47:25 +0000 |
commit | d43e6df10b85ee4a4dfd8dc164eff1177d4eb8d2 (patch) | |
tree | ccd2c209bccb917294bd1e2249f2ad0dbd949ac3 /test/CodeGen/NVPTX/machine-sink.ll | |
parent | e2cf6dc5c9193f52354aedd728a2a43ff5ebaa3b (diff) |
[MachineSink] Use the real post dominator tree
Summary:
Fixes a FIXME in MachineSinking. Instead of using the simple heuristics
in isPostDominatedBy, use the real MachinePostDominatorTree. The old
heuristics caused instructions to sink unnecessarily, and might create
register pressure.
Test Plan:
Added a NVPTX codegen test to verify that our change is in effect. It also
shows the unnecessary register pressure caused by over-sinking. Updated
affected tests in AArch64 and X86.
Reviewers: eliben, meheff, Jiangning
Reviewed By: Jiangning
Subscribers: jholewinski, aemerson, mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D4814
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216862 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/NVPTX/machine-sink.ll')
-rw-r--r-- | test/CodeGen/NVPTX/machine-sink.ll | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/test/CodeGen/NVPTX/machine-sink.ll b/test/CodeGen/NVPTX/machine-sink.ll new file mode 100644 index 00000000000..3614bea1653 --- /dev/null +++ b/test/CodeGen/NVPTX/machine-sink.ll @@ -0,0 +1,40 @@ +; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s + +target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64" + +@scalar1 = internal addrspace(3) global float 0.000000e+00, align 4 +@scalar2 = internal addrspace(3) global float 0.000000e+00, align 4 + +; We shouldn't sink mul.rn.f32 to BB %merge because BB %merge post-dominates +; BB %entry. Over-sinking created more register pressure on this example. The +; backend would sink the fmuls to BB %merge, but not the loads for being +; conservative on sinking memory accesses. As a result, the loads and +; the two fmuls would be separated to two basic blocks, causing two +; cross-BB live ranges. +define float @post_dominate(float %x, i1 %cond) { +; CHECK-LABEL: post_dominate( +entry: + %0 = load float* addrspacecast (float addrspace(3)* @scalar1 to float*), align 4 + %1 = load float* addrspacecast (float addrspace(3)* @scalar2 to float*), align 4 +; CHECK: ld.shared.f32 +; CHECK: ld.shared.f32 + %2 = fmul float %0, %0 + %3 = fmul float %1, %2 +; CHECK-NOT: bra +; CHECK: mul.rn.f32 +; CHECK: mul.rn.f32 + br i1 %cond, label %then, label %merge + +then: + %z = fadd float %x, %x + br label %then2 + +then2: + %z2 = fadd float %z, %z + br label %merge + +merge: + %y = phi float [ 0.0, %entry ], [ %z2, %then2 ] + %w = fadd float %y, %3 + ret float %w +} |