mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 20:29:48 +00:00
bd1729e5d4
This patch teaches X86FastISel how to select AVX instructions for scalar
float/double convert operations.
Before this patch, X86FastISel always selected legacy SSE instructions
for FPExt (from float to double) and FPTrunc (from double to float).
For example:
\code
define double @foo(float %f) {
%conv = fpext float %f to double
ret double %conv
}
\end code
Before (with -mattr=+avx -fast-isel) X86FastIsel selected a CVTSS2SDrr which is
legacy SSE:
cvtss2sd %xmm0, %xmm0
With this patch, X86FastIsel selects a VCVTSS2SDrr instead:
vcvtss2sd %xmm0, %xmm0, %xmm0
Added test fast-isel-fptrunc-fpext.ll to check both the register-register and
the register-memory float/double conversion variants.
Differential Revision: http://reviews.llvm.org/D7438
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228682 91177308-0d34-0410-b5e6-96231b3b80d8
66 lines
1.7 KiB
LLVM
66 lines
1.7 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 -fast-isel | FileCheck %s --check-prefix=ALL --check-prefix=SSE
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx -fast-isel | FileCheck %s --check-prefix=ALL --check-prefix=AVX
|
|
;
|
|
; Verify that fast-isel doesn't select legacy SSE instructions on targets that
|
|
; feature AVX.
|
|
;
|
|
; Test cases are obtained from the following code snippet:
|
|
; ///
|
|
; double single_to_double_rr(float x) {
|
|
; return (double)x;
|
|
; }
|
|
; float double_to_single_rr(double x) {
|
|
; return (float)x;
|
|
; }
|
|
; double single_to_double_rm(float *x) {
|
|
; return (double)*x;
|
|
; }
|
|
; float double_to_single_rm(double *x) {
|
|
; return (float)*x;
|
|
; }
|
|
; ///
|
|
|
|
define double @single_to_double_rr(float %x) {
|
|
; ALL-LABEL: single_to_double_rr:
|
|
; SSE-NOT: vcvtss2sd
|
|
; AVX: vcvtss2sd %xmm0, %xmm0, %xmm0
|
|
; ALL: ret
|
|
entry:
|
|
%conv = fpext float %x to double
|
|
ret double %conv
|
|
}
|
|
|
|
define float @double_to_single_rr(double %x) {
|
|
; ALL-LABEL: double_to_single_rr:
|
|
; SSE-NOT: vcvtsd2ss
|
|
; AVX: vcvtsd2ss %xmm0, %xmm0, %xmm0
|
|
; ALL: ret
|
|
entry:
|
|
%conv = fptrunc double %x to float
|
|
ret float %conv
|
|
}
|
|
|
|
define double @single_to_double_rm(float* %x) {
|
|
; ALL-LABEL: single_to_double_rm:
|
|
; SSE: cvtss2sd (%rdi), %xmm0
|
|
; AVX: vmovss (%rdi), %xmm0
|
|
; AVX-NEXT: vcvtss2sd %xmm0, %xmm0, %xmm0
|
|
; ALL-NEXT: ret
|
|
entry:
|
|
%0 = load float* %x, align 4
|
|
%conv = fpext float %0 to double
|
|
ret double %conv
|
|
}
|
|
|
|
define float @double_to_single_rm(double* %x) {
|
|
; ALL-LABEL: double_to_single_rm:
|
|
; SSE: cvtsd2ss (%rdi), %xmm0
|
|
; AVX: vmovsd (%rdi), %xmm0
|
|
; AVX-NEXT: vcvtsd2ss %xmm0, %xmm0, %xmm0
|
|
; ALL-NEXT: ret
|
|
entry:
|
|
%0 = load double* %x, align 8
|
|
%conv = fptrunc double %0 to float
|
|
ret float %conv
|
|
}
|