mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
fba10ebb96
The ISD::STRICT_ nodes used to implement the constrained floating-point intrinsics are currently never passed to the target back-end, which makes it impossible to handle them correctly (e.g. mark instructions are depending on a floating-point status and control register, or mark instructions as possibly trapping). This patch allows the target to use setOperationAction to switch the action on ISD::STRICT_ nodes to Legal. If this is done, the SelectionDAG common code will stop converting the STRICT nodes to regular floating-point nodes, but instead pass the STRICT nodes to the target using normal SelectionDAG matching rules. To avoid having the back-end duplicate all the floating-point instruction patterns to handle both strict and non-strict variants, we make the MI codegen explicitly aware of the floating-point exceptions by introducing two new concepts: - A new MCID flag "mayRaiseFPException" that the target should set on any instruction that possibly can raise FP exception according to the architecture definition. - A new MI flag FPExcept that CodeGen/SelectionDAG will set on any MI instruction resulting from expansion of any constrained FP intrinsic. Any MI instruction that is *both* marked as mayRaiseFPException *and* FPExcept then needs to be considered as raising exceptions by MI-level codegen (e.g. scheduling). Setting those two new flags is straightforward. The mayRaiseFPException flag is simply set via TableGen by marking all relevant instruction patterns in the .td files. The FPExcept flag is set in SDNodeFlags when creating the STRICT_ nodes in the SelectionDAG, and gets inherited in the MachineSDNode nodes created from it during instruction selection. The flag is then transfered to an MIFlag when creating the MI from the MachineSDNode. This is handled just like fast-math flags like no-nans are handled today. This patch includes both common code changes required to implement the new features, and the SystemZ implementation. Reviewed By: andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D55506 llvm-svn: 362663
38 lines
1.4 KiB
LLVM
38 lines
1.4 KiB
LLVM
; Test strict vector multiply-and-add on z14.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z14 | FileCheck %s
|
|
|
|
declare <4 x float> @llvm.experimental.constrained.fma.v4f32(<4 x float>, <4 x float>, <4 x float>, metadata, metadata)
|
|
|
|
; Test a v4f32 multiply-and-add.
|
|
define <4 x float> @f1(<4 x float> %dummy, <4 x float> %val1,
|
|
<4 x float> %val2, <4 x float> %val3) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: vfmasb %v24, %v26, %v28, %v30
|
|
; CHECK: br %r14
|
|
%ret = call <4 x float> @llvm.experimental.constrained.fma.v4f32 (
|
|
<4 x float> %val1,
|
|
<4 x float> %val2,
|
|
<4 x float> %val3,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict")
|
|
ret <4 x float> %ret
|
|
}
|
|
|
|
; Test a v4f32 multiply-and-subtract.
|
|
define <4 x float> @f2(<4 x float> %dummy, <4 x float> %val1,
|
|
<4 x float> %val2, <4 x float> %val3) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: vfmssb %v24, %v26, %v28, %v30
|
|
; CHECK: br %r14
|
|
%negval3 = fsub <4 x float> <float -0.0, float -0.0,
|
|
float -0.0, float -0.0>, %val3
|
|
%ret = call <4 x float> @llvm.experimental.constrained.fma.v4f32 (
|
|
<4 x float> %val1,
|
|
<4 x float> %val2,
|
|
<4 x float> %negval3,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict")
|
|
ret <4 x float> %ret
|
|
}
|