From 31f9eb59e568af9c0a74927727f206775ea3da55 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Wed, 18 May 2011 22:12:28 +0000 Subject: [PATCH] Properly handle 256bit load cast. gcc/ 2011-05-18 H.J. Lu PR target/49002 * config/i386/sse.md (avx__): Properly handle load cast. gcc/testsuite/ 2011-05-18 H.J. Lu PR target/49002 * gcc.target/i386/pr49002-1.c: New test. * gcc.target/i386/pr49002-2.c: Likewise. From-SVN: r173880 --- gcc/ChangeLog | 6 ++++++ gcc/config/i386/sse.md | 9 +++++---- gcc/testsuite/ChangeLog | 6 ++++++ gcc/testsuite/gcc.target/i386/pr49002-1.c | 16 ++++++++++++++++ gcc/testsuite/gcc.target/i386/pr49002-2.c | 14 ++++++++++++++ 5 files changed, 47 insertions(+), 4 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr49002-1.c create mode 100644 gcc/testsuite/gcc.target/i386/pr49002-2.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 0850640b837..c695f9b7998 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,9 @@ +2011-05-18 H.J. Lu + + PR target/49002 + * config/i386/sse.md (avx__): + Properly handle load cast. + 2011-05-18 Jakub Jelinek PR tree-optimization/49039 diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 291bffb636e..cf12a6d0c04 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -10294,12 +10294,13 @@ "&& reload_completed" [(const_int 0)] { + rtx op0 = operands[0]; rtx op1 = operands[1]; - if (REG_P (op1)) + if (REG_P (op0)) + op0 = gen_rtx_REG (mode, REGNO (op0)); + else op1 = gen_rtx_REG (mode, REGNO (op1)); - else - op1 = gen_lowpart (mode, op1); - emit_move_insn (operands[0], op1); + emit_move_insn (op0, op1); DONE; }) diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index bf4107cc42d..649ac62f689 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,9 @@ +2011-05-18 H.J. Lu + + PR target/49002 + * gcc.target/i386/pr49002-1.c: New test. + * gcc.target/i386/pr49002-2.c: Likewise. + 2011-05-18 Jakub Jelinek PR tree-optimization/49039 diff --git a/gcc/testsuite/gcc.target/i386/pr49002-1.c b/gcc/testsuite/gcc.target/i386/pr49002-1.c new file mode 100644 index 00000000000..7553e8290e5 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr49002-1.c @@ -0,0 +1,16 @@ +/* PR target/49002 */ +/* { dg-do compile } */ +/* { dg-options "-O -mavx" } */ + +#include + +void foo(const __m128d *from, __m256d *to, int s) +{ + __m256d var = _mm256_castpd128_pd256(from[0]); + var = _mm256_insertf128_pd(var, from[s], 1); + to[0] = var; +} + +/* Ensure we load into xmm, not ymm. */ +/* { dg-final { scan-assembler-not "vmovapd\[\t \]*\[^,\]*,\[\t \]*%ymm" } } */ +/* { dg-final { scan-assembler "vmovapd\[\t \]*\[^,\]*,\[\t \]*%xmm" } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr49002-2.c b/gcc/testsuite/gcc.target/i386/pr49002-2.c new file mode 100644 index 00000000000..b0e10091b5c --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr49002-2.c @@ -0,0 +1,14 @@ +/* PR target/49002 */ +/* { dg-do compile } */ +/* { dg-options "-O -mavx" } */ + +#include + +void foo(const __m128d from, __m256d *to) +{ + *to = _mm256_castpd128_pd256(from); +} + +/* Ensure we store ymm, not xmm. */ +/* { dg-final { scan-assembler-not "vmovapd\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */ +/* { dg-final { scan-assembler "vmovapd\[\t \]*%ymm\[0-9\]\+,\[^,\]*" } } */ -- 2.30.2