From c3277a88285e5e40e6d5ee9da7342fae42eaf82e Mon Sep 17 00:00:00 2001
From: Sander de Smalen <sander.desmalen@arm.com>
Date: Sat, 24 Jul 2021 13:41:40 +0100
Subject: [PATCH] [BasicTTI] Set scalarization cost of scalable vector casts to
 Invalid.

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
---
 llvm/include/llvm/CodeGen/BasicTTIImpl.h          |  4 +++
 llvm/test/Analysis/CostModel/AArch64/sve-fptoi.ll | 38 +++++++++++++++++++++++
 2 files changed, 42 insertions(+)

diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 66e0f5f..f5557a2 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -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();
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-fptoi.ll b/llvm/test/Analysis/CostModel/AArch64/sve-fptoi.ll
index 4715eaa..ee96085 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-fptoi.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-fptoi.ll
@@ -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>
-- 
2.7.4