mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2026-04-27 04:18:42 +00:00
Hans Wennborg
231d4f51d4
------------------------------------------------------------------------ r227815 | spatel | 2015-02-02 09:47:30 -0800 (Mon, 02 Feb 2015) | 2 lines fix typo ------------------------------------------------------------------------ ------------------------------------------------------------------------ r227972 | spatel | 2015-02-03 07:37:18 -0800 (Tue, 03 Feb 2015) | 10 lines Improve test to actually check for a folded load. This test was checking for lack of a "movaps" (an aligned load) rather than a "movups" (an unaligned load). It also included a store which complicated the checking. Add specific CPU runs to prevent subtarget feature flag overrides from inhibiting this optimization. ------------------------------------------------------------------------ ------------------------------------------------------------------------ r227983 | spatel | 2015-02-03 09:13:04 -0800 (Tue, 03 Feb 2015) | 22 lines Fix program crashes due to alignment exceptions generated for SSE memop instructions (PR22371). r224330 introduced a bug by misinterpreting the "FeatureVectorUAMem" bit. The commit log says that change did not affect anything, but that's not correct. That change allowed SSE instructions to have unaligned mem operands folded into math ops, and that's not allowed in the default specification for any SSE variant. The bug is exposed when compiling for an AVX-capable CPU that had this feature flag but without enabling AVX codegen. Another mistake in r224330 was not adding the feature flag to all AVX CPUs; the AMD chips were excluded. This is part of the fix for PR22371 ( http://llvm.org/bugs/show_bug.cgi?id=22371 ). This feature bit is SSE-specific, so I've renamed it to "FeatureSSEUnalignedMem". Changed the existing test case for the feature bit to reflect the new name and renamed the test file itself to better reflect the feature. Added runs to fold-vex.ll to check for the failing codegen. Note that the feature bit is not set by default on any CPU because it may require a configuration register setting to enable the enhanced unaligned behavior. ------------------------------------------------------------------------ git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@228323 91177308-0d34-0410-b5e6-96231b3b80d8
14 lines
477 B
LLVM
14 lines
477 B
LLVM
; RUN: llc -mcpu=yonah -mattr=sse-unaligned-mem -march=x86 < %s | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
define <4 x float> @foo(<4 x float>* %P, <4 x float> %In) nounwind {
|
|
%A = load <4 x float>* %P, align 4
|
|
%B = fadd <4 x float> %A, %In
|
|
ret <4 x float> %B
|
|
|
|
; CHECK-LABEL: @foo
|
|
; CHECK: addps (
|
|
}
|