[DAG] Improve simplifyDivRem's handling of zero numerators #163531
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Post legalization, simplifyDivRem will not work as well when folding zero numerators. This is due to how we disallow truncation when calling isConstOrConstSplat, similar to PR162706. Fix this by refactoring the code to use `isZeroOrZeroSplat`, which allows truncation by default.
Member
|
@llvm/pr-subscribers-llvm-selectiondag Author: Hari Limaye (hazzlim) ChangesPost legalization, simplifyDivRem will not work as well when folding Fix this by refactoring the code to use Full diff: https://github.com/llvm/llvm-project/pull/163531.diff 2 Files Affected:
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 358e060d2c6d3..30421f7173211 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -5060,8 +5060,7 @@ static SDValue simplifyDivRem(SDNode *N, SelectionDAG &DAG) {
// 0 / X -> 0
// 0 % X -> 0
- ConstantSDNode *N0C = isConstOrConstSplat(N0);
- if (N0C && N0C->isZero())
+ if (isZeroOrZeroSplat(N0))
return N0;
// X / X -> 1
diff --git a/llvm/test/CodeGen/AArch64/combine-sdiv.ll b/llvm/test/CodeGen/AArch64/combine-sdiv.ll
index cca190f08df2b..442fc1bb15e7f 100644
--- a/llvm/test/CodeGen/AArch64/combine-sdiv.ll
+++ b/llvm/test/CodeGen/AArch64/combine-sdiv.ll
@@ -1859,3 +1859,43 @@ define <16 x i16> @combine_vec_sdiv_by_one_obfuscated(<16 x i16> %x) "target-fea
%div = sdiv <16 x i16> %x, %zero_and_ones
ret <16 x i16> %div
}
+
+define <8 x i32> @combine_vec_sdiv_zero_obfuscated(<8 x i32> %x) {
+; CHECK-SD-LABEL: combine_vec_sdiv_zero_obfuscated:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: fmov w10, s0
+; CHECK-SD-NEXT: mov w8, #1 // =0x1
+; CHECK-SD-NEXT: mov w9, v0.s[1]
+; CHECK-SD-NEXT: mov w11, v0.s[2]
+; CHECK-SD-NEXT: mov w12, v0.s[3]
+; CHECK-SD-NEXT: movi v1.2d, #0000000000000000
+; CHECK-SD-NEXT: sdiv w10, w8, w10
+; CHECK-SD-NEXT: sdiv w9, w8, w9
+; CHECK-SD-NEXT: fmov s0, w10
+; CHECK-SD-NEXT: sdiv w11, w8, w11
+; CHECK-SD-NEXT: mov v0.s[1], w9
+; CHECK-SD-NEXT: sdiv w8, w8, w12
+; CHECK-SD-NEXT: mov v0.s[2], w11
+; CHECK-SD-NEXT: mov v0.s[3], w8
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: combine_vec_sdiv_zero_obfuscated:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: fmov w9, s0
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: mov w10, v0.s[1]
+; CHECK-GI-NEXT: mov w11, v0.s[2]
+; CHECK-GI-NEXT: mov w12, v0.s[3]
+; CHECK-GI-NEXT: movi v1.2d, #0000000000000000
+; CHECK-GI-NEXT: sdiv w9, w8, w9
+; CHECK-GI-NEXT: sdiv w10, w8, w10
+; CHECK-GI-NEXT: fmov s0, w9
+; CHECK-GI-NEXT: sdiv w11, w8, w11
+; CHECK-GI-NEXT: mov v0.s[1], w10
+; CHECK-GI-NEXT: sdiv w8, w8, w12
+; CHECK-GI-NEXT: mov v0.s[2], w11
+; CHECK-GI-NEXT: mov v0.s[3], w8
+; CHECK-GI-NEXT: ret
+ %1 = sdiv <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 0, i32 0, i32 0, i32 0>, %x
+ ret <8 x i32> %1
+}
|
Member
|
@llvm/pr-subscribers-backend-aarch64 Author: Hari Limaye (hazzlim) ChangesPost legalization, simplifyDivRem will not work as well when folding Fix this by refactoring the code to use Full diff: https://github.com/llvm/llvm-project/pull/163531.diff 2 Files Affected:
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 358e060d2c6d3..30421f7173211 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -5060,8 +5060,7 @@ static SDValue simplifyDivRem(SDNode *N, SelectionDAG &DAG) {
// 0 / X -> 0
// 0 % X -> 0
- ConstantSDNode *N0C = isConstOrConstSplat(N0);
- if (N0C && N0C->isZero())
+ if (isZeroOrZeroSplat(N0))
return N0;
// X / X -> 1
diff --git a/llvm/test/CodeGen/AArch64/combine-sdiv.ll b/llvm/test/CodeGen/AArch64/combine-sdiv.ll
index cca190f08df2b..442fc1bb15e7f 100644
--- a/llvm/test/CodeGen/AArch64/combine-sdiv.ll
+++ b/llvm/test/CodeGen/AArch64/combine-sdiv.ll
@@ -1859,3 +1859,43 @@ define <16 x i16> @combine_vec_sdiv_by_one_obfuscated(<16 x i16> %x) "target-fea
%div = sdiv <16 x i16> %x, %zero_and_ones
ret <16 x i16> %div
}
+
+define <8 x i32> @combine_vec_sdiv_zero_obfuscated(<8 x i32> %x) {
+; CHECK-SD-LABEL: combine_vec_sdiv_zero_obfuscated:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: fmov w10, s0
+; CHECK-SD-NEXT: mov w8, #1 // =0x1
+; CHECK-SD-NEXT: mov w9, v0.s[1]
+; CHECK-SD-NEXT: mov w11, v0.s[2]
+; CHECK-SD-NEXT: mov w12, v0.s[3]
+; CHECK-SD-NEXT: movi v1.2d, #0000000000000000
+; CHECK-SD-NEXT: sdiv w10, w8, w10
+; CHECK-SD-NEXT: sdiv w9, w8, w9
+; CHECK-SD-NEXT: fmov s0, w10
+; CHECK-SD-NEXT: sdiv w11, w8, w11
+; CHECK-SD-NEXT: mov v0.s[1], w9
+; CHECK-SD-NEXT: sdiv w8, w8, w12
+; CHECK-SD-NEXT: mov v0.s[2], w11
+; CHECK-SD-NEXT: mov v0.s[3], w8
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: combine_vec_sdiv_zero_obfuscated:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: fmov w9, s0
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: mov w10, v0.s[1]
+; CHECK-GI-NEXT: mov w11, v0.s[2]
+; CHECK-GI-NEXT: mov w12, v0.s[3]
+; CHECK-GI-NEXT: movi v1.2d, #0000000000000000
+; CHECK-GI-NEXT: sdiv w9, w8, w9
+; CHECK-GI-NEXT: sdiv w10, w8, w10
+; CHECK-GI-NEXT: fmov s0, w9
+; CHECK-GI-NEXT: sdiv w11, w8, w11
+; CHECK-GI-NEXT: mov v0.s[1], w10
+; CHECK-GI-NEXT: sdiv w8, w8, w12
+; CHECK-GI-NEXT: mov v0.s[2], w11
+; CHECK-GI-NEXT: mov v0.s[3], w8
+; CHECK-GI-NEXT: ret
+ %1 = sdiv <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 0, i32 0, i32 0, i32 0>, %x
+ ret <8 x i32> %1
+}
|
Collaborator
|
When I look at just the second commit I don't see any changes to the output for the new tests? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Post legalization, simplifyDivRem will not work as well when folding
zero numerators. This is due to how we disallow truncation when calling
isConstOrConstSplat, similar to PR162706.
Fix this by refactoring the code to use
isZeroOrZeroSplat, whichallows truncation by default.