From 502775a2ee08e2fe1df7dd0741722a31debffa16 Mon Sep 17 00:00:00 2001 From: Akira Hatanaka Date: Sat, 9 Dec 2017 00:02:37 +0000 Subject: [CodeGen][X86] Fix handling of __fp16 vectors. This commit fixes a bug in IRGen where it generates completely broken code for __fp16 vectors on X86. For example when the following code is compiled: half4 hv0, hv1, hv2; // these are vectors of __fp16. void foo221() { hv0 = hv1 + hv2; } clang generates the following IR, in which two i16 vectors are added: @hv1 = common global <4 x i16> zeroinitializer, align 8 @hv2 = common global <4 x i16> zeroinitializer, align 8 @hv0 = common global <4 x i16> zeroinitializer, align 8 define void @foo221() { %0 = load <4 x i16>, <4 x i16>* @hv1, align 8 %1 = load <4 x i16>, <4 x i16>* @hv2, align 8 %add = add <4 x i16> %0, %1 store <4 x i16> %add, <4 x i16>* @hv0, align 8 ret void } To fix the bug, this commit uses the code committed in r314056, which modified clang to promote and truncate __fp16 vectors to and from float vectors in the AST. It also fixes another IRGen bug where a short value is assigned to an __fp16 variable without any integer-to-floating-point conversion, as shown in the following example: __fp16 a; short b; void foo1() { a = b; } @b = common global i16 0, align 2 @a = common global i16 0, align 2 define void @foo1() #0 { %0 = load i16, i16* @b, align 2 store i16 %0, i16* @a, align 2 ret void } rdar://problem/20625184 Differential Revision: https://reviews.llvm.org/D40112 llvm-svn: 320215 --- clang/test/CodeGen/fp16vec-ops.c | 1 + 1 file changed, 1 insertion(+) (limited to 'clang/test/CodeGen/fp16vec-ops.c') diff --git a/clang/test/CodeGen/fp16vec-ops.c b/clang/test/CodeGen/fp16vec-ops.c index a99be4154bf..2eb75a48e30 100644 --- a/clang/test/CodeGen/fp16vec-ops.c +++ b/clang/test/CodeGen/fp16vec-ops.c @@ -1,6 +1,7 @@ // REQUIRES: arm-registered-target // RUN: %clang_cc1 -triple arm64-apple-ios9 -emit-llvm -o - -fallow-half-arguments-and-returns %s | FileCheck %s --check-prefix=CHECK // RUN: %clang_cc1 -triple armv7-apple-ios9 -emit-llvm -o - -fallow-half-arguments-and-returns %s | FileCheck %s --check-prefix=CHECK +// RUN: %clang_cc1 -triple x86_64-apple-macos10.13 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK typedef __fp16 half4 __attribute__ ((vector_size (8))); typedef short short4 __attribute__ ((vector_size (8))); -- cgit v1.2.3