OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

[X86] Remove patterns for selecting a v8f32 X86ISD::MOVSS or v4f64 X86ISD::MOVSD. 

I don't think we ever generate these. If we did, I would expect we would also be able to generate v16f32 and v8f64, but we don't have those patterns.

llvm-svn: 312694
This commit is contained in:
Craig Topper 2017-09-07 05:08:16 +00:00
parent 064028bb05
commit 9228aee711
2 changed files with 0 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
llvm/lib/Target/X86/X86InstrAVX512.td
View File

@ -4283,36 +4283,12 @@ let Predicates = [HasAVX512] in {
(VMOVSSZrr (v4f32 VR128X:$src1), (VMOVSSZrr (v4f32 VR128X:$src1),
(COPY_TO_REGCLASS (v4f32 VR128X:$src2), FR32X))>; (COPY_TO_REGCLASS (v4f32 VR128X:$src2), FR32X))>;
// 256-bit variants
def : Pat<(v8i32 (X86Movss VR256X:$src1, VR256X:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSSZrr (EXTRACT_SUBREG (v8i32 VR256X:$src1), sub_xmm),
(EXTRACT_SUBREG (v8i32 VR256X:$src2), sub_xmm)),
sub_xmm)>;
def : Pat<(v8f32 (X86Movss VR256X:$src1, VR256X:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSSZrr (EXTRACT_SUBREG (v8f32 VR256X:$src1), sub_xmm),
(EXTRACT_SUBREG (v8f32 VR256X:$src2), sub_xmm)),
sub_xmm)>;
// Shuffle with VMOVSD // Shuffle with VMOVSD
def : Pat<(v2i64 (X86Movsd VR128X:$src1, VR128X:$src2)), def : Pat<(v2i64 (X86Movsd VR128X:$src1, VR128X:$src2)),
(VMOVSDZrr VR128X:$src1, (COPY_TO_REGCLASS VR128X:$src2, FR64X))>; (VMOVSDZrr VR128X:$src1, (COPY_TO_REGCLASS VR128X:$src2, FR64X))>;
def : Pat<(v2f64 (X86Movsd VR128X:$src1, VR128X:$src2)), def : Pat<(v2f64 (X86Movsd VR128X:$src1, VR128X:$src2)),
(VMOVSDZrr VR128X:$src1, (COPY_TO_REGCLASS VR128X:$src2, FR64X))>; (VMOVSDZrr VR128X:$src1, (COPY_TO_REGCLASS VR128X:$src2, FR64X))>;
// 256-bit variants
def : Pat<(v4i64 (X86Movsd VR256X:$src1, VR256X:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSDZrr (EXTRACT_SUBREG (v4i64 VR256X:$src1), sub_xmm),
(EXTRACT_SUBREG (v4i64 VR256X:$src2), sub_xmm)),
sub_xmm)>;
def : Pat<(v4f64 (X86Movsd VR256X:$src1, VR256X:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSDZrr (EXTRACT_SUBREG (v4f64 VR256X:$src1), sub_xmm),
(EXTRACT_SUBREG (v4f64 VR256X:$src2), sub_xmm)),
sub_xmm)>;
def : Pat<(v2f64 (X86Movlpd VR128X:$src1, VR128X:$src2)), def : Pat<(v2f64 (X86Movlpd VR128X:$src1, VR128X:$src2)),
(VMOVSDZrr VR128X:$src1, (COPY_TO_REGCLASS VR128X:$src2, FR64X))>; (VMOVSDZrr VR128X:$src1, (COPY_TO_REGCLASS VR128X:$src2, FR64X))>;
def : Pat<(v2i64 (X86Movlpd VR128X:$src1, VR128X:$src2)), def : Pat<(v2i64 (X86Movlpd VR128X:$src1, VR128X:$src2)),

24
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -512,36 +512,12 @@ let Predicates = [UseAVX] in {
(VMOVSSrr (v4f32 VR128:$src1), (VMOVSSrr (v4f32 VR128:$src1),
(COPY_TO_REGCLASS (v4f32 VR128:$src2), FR32))>; (COPY_TO_REGCLASS (v4f32 VR128:$src2), FR32))>;
// 256-bit variants
def : Pat<(v8i32 (X86Movss VR256:$src1, VR256:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSSrr (EXTRACT_SUBREG (v8i32 VR256:$src1), sub_xmm),
(EXTRACT_SUBREG (v8i32 VR256:$src2), sub_xmm)),
sub_xmm)>;
def : Pat<(v8f32 (X86Movss VR256:$src1, VR256:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSSrr (EXTRACT_SUBREG (v8f32 VR256:$src1), sub_xmm),
(EXTRACT_SUBREG (v8f32 VR256:$src2), sub_xmm)),
sub_xmm)>;
// Shuffle with VMOVSD // Shuffle with VMOVSD
def : Pat<(v2i64 (X86Movsd VR128:$src1, VR128:$src2)), def : Pat<(v2i64 (X86Movsd VR128:$src1, VR128:$src2)),
(VMOVSDrr VR128:$src1, (COPY_TO_REGCLASS VR128:$src2, FR64))>; (VMOVSDrr VR128:$src1, (COPY_TO_REGCLASS VR128:$src2, FR64))>;
def : Pat<(v2f64 (X86Movsd VR128:$src1, VR128:$src2)), def : Pat<(v2f64 (X86Movsd VR128:$src1, VR128:$src2)),
(VMOVSDrr VR128:$src1, (COPY_TO_REGCLASS VR128:$src2, FR64))>; (VMOVSDrr VR128:$src1, (COPY_TO_REGCLASS VR128:$src2, FR64))>;
// 256-bit variants
def : Pat<(v4i64 (X86Movsd VR256:$src1, VR256:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSDrr (EXTRACT_SUBREG (v4i64 VR256:$src1), sub_xmm),
(EXTRACT_SUBREG (v4i64 VR256:$src2), sub_xmm)),
sub_xmm)>;
def : Pat<(v4f64 (X86Movsd VR256:$src1, VR256:$src2)),
(SUBREG_TO_REG (i32 0),
(VMOVSDrr (EXTRACT_SUBREG (v4f64 VR256:$src1), sub_xmm),
(EXTRACT_SUBREG (v4f64 VR256:$src2), sub_xmm)),
sub_xmm)>;
// FIXME: Instead of a X86Movlps there should be a X86Movsd here, the problem // FIXME: Instead of a X86Movlps there should be a X86Movsd here, the problem
// is during lowering, where it's not possible to recognize the fold cause // is during lowering, where it's not possible to recognize the fold cause
// it has two uses through a bitcast. One use disappears at isel time and the // it has two uses through a bitcast. One use disappears at isel time and the