RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 12:41:49 +01:00
Code Issues Projects Releases Wiki Activity

[BasicTTI] Set scalarization cost of scalable vector casts to Invalid.

Browse Source 
When BasicTTIImpl::getCastInstrCost can't determine the cost of a
vector cast operation when the types need legalization, it falls
back to calculating scalarization costs. Instead of crashing on
`cast<FixedVectorType>(DstVTy)` when the type is a scalable vector,
return an Invalid cost.

Reviewed By: david-arm

Differential Revision: https://reviews.llvm.org/D106655
This commit is contained in:
Sander de Smalen 2021-07-24 13:41:40 +01:00
parent d69614109a
commit 1f523effc3
2 changed files with 42 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
include/llvm/CodeGen/BasicTTIImpl.h
View File

@ -1004,6 +1004,10 @@ public:
CostKind, I));
}
// Scalarization cost is Invalid, can't assume any num elements.
if (isa<ScalableVectorType>(DstVTy))
return InstructionCost::getInvalid();
// In other cases where the source or destination are illegal, assume
// the operation will get scalarized.
unsigned Num = cast<FixedVectorType>(DstVTy)->getNumElements();

38
test/Analysis/CostModel/AArch64/sve-fptoi.ll
View File

@ -5,6 +5,24 @@ target triple = "aarch64-unknown-linux-gnu"
define void @sve-fptoi() {
; CHECK-LABEL: 'sve-fptoi'
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f16_to_si8 = fptosi <vscale x 1 x half> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f16_to_ui8 = fptoui <vscale x 1 x half> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f16_to_si32 = fptosi <vscale x 1 x half> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f16_to_ui32 = fptoui <vscale x 1 x half> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f16_to_si64 = fptosi <vscale x 1 x half> undef to <vscale x 1 x i64>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f16_to_ui64 = fptoui <vscale x 1 x half> undef to <vscale x 1 x i64>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f32_to_si8 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f32_to_ui8 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f32_to_si16 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f32_to_ui16 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f32_to_si64 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i64>
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %nv1f32_to_ui64 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i64>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv1f64_to_si8 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv1f64_to_ui8 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv1f64_to_si16 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv1f64_to_ui16 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv1f64_to_si32 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv1f64_to_ui32 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv2f16_to_si8 = fptosi <vscale x 2 x half> undef to <vscale x 2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv2f16_to_ui8 = fptoui <vscale x 2 x half> undef to <vscale x 2 x i8>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nv2f16_to_si32 = fptosi <vscale x 2 x half> undef to <vscale x 2 x i32>
@ -59,6 +77,26 @@ define void @sve-fptoi() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %nv8f64_to_ui16 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nv8f64_to_si32 = fptosi <vscale x 8 x double> undef to <vscale x 8 x i32>
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %nv8f64_to_ui32 = fptoui <vscale x 8 x double> undef to <vscale x 8 x i32>
%nv1f16_to_si8 = fptosi <vscale x 1 x half> undef to <vscale x 1 x i8>
%nv1f16_to_ui8 = fptoui <vscale x 1 x half> undef to <vscale x 1 x i8>
%nv1f16_to_si32 = fptosi <vscale x 1 x half> undef to <vscale x 1 x i32>
%nv1f16_to_ui32 = fptoui <vscale x 1 x half> undef to <vscale x 1 x i32>
%nv1f16_to_si64 = fptosi <vscale x 1 x half> undef to <vscale x 1 x i64>
%nv1f16_to_ui64 = fptoui <vscale x 1 x half> undef to <vscale x 1 x i64>
%nv1f32_to_si8 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i8>
%nv1f32_to_ui8 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i8>
%nv1f32_to_si16 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i16>
%nv1f32_to_ui16 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i16>
%nv1f32_to_si64 = fptosi <vscale x 1 x float> undef to <vscale x 1 x i64>
%nv1f32_to_ui64 = fptoui <vscale x 1 x float> undef to <vscale x 1 x i64>
%nv1f64_to_si8 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i8>
%nv1f64_to_ui8 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i8>
%nv1f64_to_si16 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i16>
%nv1f64_to_ui16 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i16>
%nv1f64_to_si32 = fptosi <vscale x 1 x double> undef to <vscale x 1 x i32>
%nv1f64_to_ui32 = fptoui <vscale x 1 x double> undef to <vscale x 1 x i32>
%nv2f16_to_si8 = fptosi <vscale x 2 x half> undef to <vscale x 2 x i8>
%nv2f16_to_ui8 = fptoui <vscale x 2 x half> undef to <vscale x 2 x i8>