[llvm] c65270c - [AArch64] Add basic umulo and smulo costs
David Green via llvm-commits
llvm-commits at lists.llvm.org
Thu Jan 6 09:22:51 PST 2022
Author: David Green
Date: 2022-01-06T17:22:47Z
New Revision: c65270cf96b7c19141f33e9d16eb7adf989b638f
URL: https://github.com/llvm/llvm-project/commit/c65270cf96b7c19141f33e9d16eb7adf989b638f
DIFF: https://github.com/llvm/llvm-project/commit/c65270cf96b7c19141f33e9d16eb7adf989b638f.diff
LOG: [AArch64] Add basic umulo and smulo costs
This adds some AArch64 specific smul_with_overflow and umul_with_overflow
costs, overriding the default costs. The code generation for these mul
with overflow intrinsics is usually better than the default expansion on
AArch64. The costs come from https://godbolt.org/z/zEzYhMWqo with various
types, or llvm/test/CodeGen/AArch64/arm64-xaluo.ll.
Differential Revision: https://reviews.llvm.org/D116732
Added:
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index d21854e38f5a..d6b51f110981 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -331,6 +331,25 @@ AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
}
break;
}
+ case Intrinsic::smul_with_overflow:
+ case Intrinsic::umul_with_overflow: {
+ static const CostTblEntry WithOverflowCostTbl[] = {
+ {Intrinsic::smul_with_overflow, MVT::i8, 5},
+ {Intrinsic::umul_with_overflow, MVT::i8, 4},
+ {Intrinsic::smul_with_overflow, MVT::i16, 5},
+ {Intrinsic::umul_with_overflow, MVT::i16, 4},
+ {Intrinsic::smul_with_overflow, MVT::i32, 2}, // eg umull;tst
+ {Intrinsic::umul_with_overflow, MVT::i32, 2}, // eg umull;cmp sxtw
+ {Intrinsic::smul_with_overflow, MVT::i64, 3}, // eg mul;smulh;cmp
+ {Intrinsic::umul_with_overflow, MVT::i64, 3}, // eg mul;umulh;cmp asr
+ };
+ EVT MTy = TLI->getValueType(DL, RetTy->getContainedType(0), true);
+ if (MTy.isSimple())
+ if (const auto *Entry = CostTableLookup(WithOverflowCostTbl, ICA.getID(),
+ MTy.getSimpleVT()))
+ return Entry->Cost;
+ break;
+ }
default:
break;
}
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll b/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
index 572a8294994d..9492473e1bf3 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
@@ -352,38 +352,38 @@ declare {<64 x i8>, <64 x i1>} @llvm.smul.with.overflow.v64i8(<64 x i8>, <64 x
define i32 @smul(i32 %arg) {
; RECIP-LABEL: 'smul'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'smul'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
@@ -434,38 +434,38 @@ declare {<64 x i8>, <64 x i1>} @llvm.umul.with.overflow.v64i8(<64 x i8>, <64 x
define i32 @umul(i32 %arg) {
; RECIP-LABEL: 'umul'
-; RECIP-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'umul'
-; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
More information about the llvm-commits
mailing list