shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
David Green 2a859b2014 [AArch64] Change the cost of vector insert/extract to 2 
The cost of vector instructions has always been high under AArch64, in order to
add a high cost for inserts/extracts, shuffles and scalarization. This is a
conservative approach to limit the scope of unusual SLP vectorization where the
codegen ends up being quite poor, but has always been higher than the correct
costs would be for any specific core.

This relaxes that, reducing the vector insert/extract cost from 3 to 2. It is a
generalization of D142359 to all AArch64 cpus. The ScalarizationOverhead is
also overridden for integer vector at the same time, to remove the effect of
lane 0 being considered free for integer vectors (something that should only be
true for float when scalarizing).

The lower insert/extract cost will reduce the cost of insert, extracts,
shuffling and scalarization. The adjustments of ScalaizationOverhead will
increase the cost on integer, especially for small vectors. The end result will
be lower cost for float and long-integer types, some higher cost for some
smaller vectors. This, along with the raw insert/extract cost being lower, will
generally mean more vectorization from the Loop and SLP vectorizer.

We may end up regretting this, as that vectorization is not always profitable.
In all the benchmarking I have done this is generally an improvement in the
overall performance, and I've attempted to address the places where it wasn't
with other costmodel adjustments.

Differential Revision: https://reviews.llvm.org/D155459
2023-07-28 21:26:50 +01:00

498 lines
51 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64 < %s | FileCheck %s --check-prefix=RECIP
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=aarch64 < %s | FileCheck %s --check-prefix=SIZE
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
declare {i64, i1} @llvm.sadd.with.overflow.i64(i64, i64)
declare {<2 x i64>, <2 x i1>} @llvm.sadd.with.overflow.v2i64(<2 x i64>, <2 x i64>)
declare {<4 x i64>, <4 x i1>} @llvm.sadd.with.overflow.v4i64(<4 x i64>, <4 x i64>)
declare {<8 x i64>, <8 x i1>} @llvm.sadd.with.overflow.v8i64(<8 x i64>, <8 x i64>)
declare {i32, i1} @llvm.sadd.with.overflow.i32(i32, i32)
declare {<4 x i32>, <4 x i1>} @llvm.sadd.with.overflow.v4i32(<4 x i32>, <4 x i32>)
declare {<8 x i32>, <8 x i1>} @llvm.sadd.with.overflow.v8i32(<8 x i32>, <8 x i32>)
declare {<16 x i32>, <16 x i1>} @llvm.sadd.with.overflow.v16i32(<16 x i32>, <16 x i32>)
declare {i16, i1} @llvm.sadd.with.overflow.i16(i16, i16)
declare {<8 x i16>, <8 x i1>} @llvm.sadd.with.overflow.v8i16(<8 x i16>, <8 x i16>)
declare {<16 x i16>, <16 x i1>} @llvm.sadd.with.overflow.v16i16(<16 x i16>, <16 x i16>)
declare {<32 x i16>, <32 x i1>} @llvm.sadd.with.overflow.v32i16(<32 x i16>, <32 x i16>)
declare {i8, i1} @llvm.sadd.with.overflow.i8(i8, i8)
declare {<16 x i8>, <16 x i1>} @llvm.sadd.with.overflow.v16i8(<16 x i8>, <16 x i8>)
declare {<32 x i8>, <32 x i1>} @llvm.sadd.with.overflow.v32i8(<32 x i8>, <32 x i8>)
declare {<64 x i8>, <64 x i1>} @llvm.sadd.with.overflow.v64i8(<64 x i8>, <64 x i8>)
define i32 @sadd(i32 %arg) {
; RECIP-LABEL: 'sadd'
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.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: 'sadd'
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%I64 = call {i64, i1} @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
%V2I64 = call {<2 x i64>, <2 x i1>} @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call {<4 x i64>, <4 x i1>} @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call {<8 x i64>, <8 x i1>} @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call {i32, i1} @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
%V4I32 = call {<4 x i32>, <4 x i1>} @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call {<8 x i32>, <8 x i1>} @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call {<16 x i32>, <16 x i1>} @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call {i16, i1} @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
%V8I16 = call {<8 x i16>, <8 x i1>} @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call {<16 x i16>, <16 x i1>} @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call {<32 x i16>, <32 x i1>} @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call {i8, i1} @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
%V16I8 = call {<16 x i8>, <16 x i1>} @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call {<32 x i8>, <32 x i1>} @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call {<64 x i8>, <64 x i1>} @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
declare {i64, i1} @llvm.uadd.with.overflow.i64(i64, i64)
declare {<2 x i64>, <2 x i1>} @llvm.uadd.with.overflow.v2i64(<2 x i64>, <2 x i64>)
declare {<4 x i64>, <4 x i1>} @llvm.uadd.with.overflow.v4i64(<4 x i64>, <4 x i64>)
declare {<8 x i64>, <8 x i1>} @llvm.uadd.with.overflow.v8i64(<8 x i64>, <8 x i64>)
declare {i32, i1} @llvm.uadd.with.overflow.i32(i32, i32)
declare {<4 x i32>, <4 x i1>} @llvm.uadd.with.overflow.v4i32(<4 x i32>, <4 x i32>)
declare {<8 x i32>, <8 x i1>} @llvm.uadd.with.overflow.v8i32(<8 x i32>, <8 x i32>)
declare {<16 x i32>, <16 x i1>} @llvm.uadd.with.overflow.v16i32(<16 x i32>, <16 x i32>)
declare {i16, i1} @llvm.uadd.with.overflow.i16(i16, i16)
declare {<8 x i16>, <8 x i1>} @llvm.uadd.with.overflow.v8i16(<8 x i16>, <8 x i16>)
declare {<16 x i16>, <16 x i1>} @llvm.uadd.with.overflow.v16i16(<16 x i16>, <16 x i16>)
declare {<32 x i16>, <32 x i1>} @llvm.uadd.with.overflow.v32i16(<32 x i16>, <32 x i16>)
declare {i8, i1} @llvm.uadd.with.overflow.i8(i8, i8)
declare {<16 x i8>, <16 x i1>} @llvm.uadd.with.overflow.v16i8(<16 x i8>, <16 x i8>)
declare {<32 x i8>, <32 x i1>} @llvm.uadd.with.overflow.v32i8(<32 x i8>, <32 x i8>)
declare {<64 x i8>, <64 x i1>} @llvm.uadd.with.overflow.v64i8(<64 x i8>, <64 x i8>)
define i32 @uadd(i32 %arg) {
; RECIP-LABEL: 'uadd'
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.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: 'uadd'
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%I64 = call {i64, i1} @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
%V2I64 = call {<2 x i64>, <2 x i1>} @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call {<4 x i64>, <4 x i1>} @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call {<8 x i64>, <8 x i1>} @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
%V4I32 = call {<4 x i32>, <4 x i1>} @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call {<8 x i32>, <8 x i1>} @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call {<16 x i32>, <16 x i1>} @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call {i16, i1} @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
%V8I16 = call {<8 x i16>, <8 x i1>} @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call {<16 x i16>, <16 x i1>} @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call {<32 x i16>, <32 x i1>} @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call {i8, i1} @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
%V16I8 = call {<16 x i8>, <16 x i1>} @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call {<32 x i8>, <32 x i1>} @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call {<64 x i8>, <64 x i1>} @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
declare {i64, i1} @llvm.ssub.with.overflow.i64(i64, i64)
declare {<2 x i64>, <2 x i1>} @llvm.ssub.with.overflow.v2i64(<2 x i64>, <2 x i64>)
declare {<4 x i64>, <4 x i1>} @llvm.ssub.with.overflow.v4i64(<4 x i64>, <4 x i64>)
declare {<8 x i64>, <8 x i1>} @llvm.ssub.with.overflow.v8i64(<8 x i64>, <8 x i64>)
declare {i32, i1} @llvm.ssub.with.overflow.i32(i32, i32)
declare {<4 x i32>, <4 x i1>} @llvm.ssub.with.overflow.v4i32(<4 x i32>, <4 x i32>)
declare {<8 x i32>, <8 x i1>} @llvm.ssub.with.overflow.v8i32(<8 x i32>, <8 x i32>)
declare {<16 x i32>, <16 x i1>} @llvm.ssub.with.overflow.v16i32(<16 x i32>, <16 x i32>)
declare {i16, i1} @llvm.ssub.with.overflow.i16(i16, i16)
declare {<8 x i16>, <8 x i1>} @llvm.ssub.with.overflow.v8i16(<8 x i16>, <8 x i16>)
declare {<16 x i16>, <16 x i1>} @llvm.ssub.with.overflow.v16i16(<16 x i16>, <16 x i16>)
declare {<32 x i16>, <32 x i1>} @llvm.ssub.with.overflow.v32i16(<32 x i16>, <32 x i16>)
declare {i8, i1} @llvm.ssub.with.overflow.i8(i8, i8)
declare {<16 x i8>, <16 x i1>} @llvm.ssub.with.overflow.v16i8(<16 x i8>, <16 x i8>)
declare {<32 x i8>, <32 x i1>} @llvm.ssub.with.overflow.v32i8(<32 x i8>, <32 x i8>)
declare {<64 x i8>, <64 x i1>} @llvm.ssub.with.overflow.v64i8(<64 x i8>, <64 x i8>)
define i32 @ssub(i32 %arg) {
; RECIP-LABEL: 'ssub'
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.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: 'ssub'
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%I64 = call {i64, i1} @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
%V2I64 = call {<2 x i64>, <2 x i1>} @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call {<4 x i64>, <4 x i1>} @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call {<8 x i64>, <8 x i1>} @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call {i32, i1} @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
%V4I32 = call {<4 x i32>, <4 x i1>} @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call {<8 x i32>, <8 x i1>} @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call {<16 x i32>, <16 x i1>} @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call {i16, i1} @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
%V8I16 = call {<8 x i16>, <8 x i1>} @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call {<16 x i16>, <16 x i1>} @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call {<32 x i16>, <32 x i1>} @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call {i8, i1} @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
%V16I8 = call {<16 x i8>, <16 x i1>} @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call {<32 x i8>, <32 x i1>} @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call {<64 x i8>, <64 x i1>} @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
declare {i64, i1} @llvm.usub.with.overflow.i64(i64, i64)
declare {<2 x i64>, <2 x i1>} @llvm.usub.with.overflow.v2i64(<2 x i64>, <2 x i64>)
declare {<4 x i64>, <4 x i1>} @llvm.usub.with.overflow.v4i64(<4 x i64>, <4 x i64>)
declare {<8 x i64>, <8 x i1>} @llvm.usub.with.overflow.v8i64(<8 x i64>, <8 x i64>)
declare {i32, i1} @llvm.usub.with.overflow.i32(i32, i32)
declare {<4 x i32>, <4 x i1>} @llvm.usub.with.overflow.v4i32(<4 x i32>, <4 x i32>)
declare {<8 x i32>, <8 x i1>} @llvm.usub.with.overflow.v8i32(<8 x i32>, <8 x i32>)
declare {<16 x i32>, <16 x i1>} @llvm.usub.with.overflow.v16i32(<16 x i32>, <16 x i32>)
declare {i16, i1} @llvm.usub.with.overflow.i16(i16, i16)
declare {<8 x i16>, <8 x i1>} @llvm.usub.with.overflow.v8i16(<8 x i16>, <8 x i16>)
declare {<16 x i16>, <16 x i1>} @llvm.usub.with.overflow.v16i16(<16 x i16>, <16 x i16>)
declare {<32 x i16>, <32 x i1>} @llvm.usub.with.overflow.v32i16(<32 x i16>, <32 x i16>)
declare {i8, i1} @llvm.usub.with.overflow.i8(i8, i8)
declare {<16 x i8>, <16 x i1>} @llvm.usub.with.overflow.v16i8(<16 x i8>, <16 x i8>)
declare {<32 x i8>, <32 x i1>} @llvm.usub.with.overflow.v32i8(<32 x i8>, <32 x i8>)
declare {<64 x i8>, <64 x i1>} @llvm.usub.with.overflow.v64i8(<64 x i8>, <64 x i8>)
define i32 @usub(i32 %arg) {
; RECIP-LABEL: 'usub'
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.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: 'usub'
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%I64 = call {i64, i1} @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
%V2I64 = call {<2 x i64>, <2 x i1>} @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call {<4 x i64>, <4 x i1>} @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call {<8 x i64>, <8 x i1>} @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call {i32, i1} @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
%V4I32 = call {<4 x i32>, <4 x i1>} @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call {<8 x i32>, <8 x i1>} @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call {<16 x i32>, <16 x i1>} @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call {i16, i1} @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
%V8I16 = call {<8 x i16>, <8 x i1>} @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call {<16 x i16>, <16 x i1>} @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call {<32 x i16>, <32 x i1>} @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call {i8, i1} @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
%V16I8 = call {<16 x i8>, <16 x i1>} @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call {<32 x i8>, <32 x i1>} @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call {<64 x i8>, <64 x i1>} @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
declare {i64, i1} @llvm.smul.with.overflow.i64(i64, i64)
declare {<2 x i64>, <2 x i1>} @llvm.smul.with.overflow.v2i64(<2 x i64>, <2 x i64>)
declare {<4 x i64>, <4 x i1>} @llvm.smul.with.overflow.v4i64(<4 x i64>, <4 x i64>)
declare {<8 x i64>, <8 x i1>} @llvm.smul.with.overflow.v8i64(<8 x i64>, <8 x i64>)
declare {i32, i1} @llvm.smul.with.overflow.i32(i32, i32)
declare {<4 x i32>, <4 x i1>} @llvm.smul.with.overflow.v4i32(<4 x i32>, <4 x i32>)
declare {<8 x i32>, <8 x i1>} @llvm.smul.with.overflow.v8i32(<8 x i32>, <8 x i32>)
declare {<16 x i32>, <16 x i1>} @llvm.smul.with.overflow.v16i32(<16 x i32>, <16 x i32>)
declare {i16, i1} @llvm.smul.with.overflow.i16(i16, i16)
declare {<8 x i16>, <8 x i1>} @llvm.smul.with.overflow.v8i16(<8 x i16>, <8 x i16>)
declare {<16 x i16>, <16 x i1>} @llvm.smul.with.overflow.v16i16(<16 x i16>, <16 x i16>)
declare {<32 x i16>, <32 x i1>} @llvm.smul.with.overflow.v32i16(<32 x i16>, <32 x i16>)
declare {i8, i1} @llvm.smul.with.overflow.i8(i8, i8)
declare {<16 x i8>, <16 x i1>} @llvm.smul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
declare {<32 x i8>, <32 x i1>} @llvm.smul.with.overflow.v32i8(<32 x i8>, <32 x i8>)
declare {<64 x i8>, <64 x i1>} @llvm.smul.with.overflow.v64i8(<64 x i8>, <64 x i8>)
define i32 @smul(i32 %arg) {
; RECIP-LABEL: 'smul'
; 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 34 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 68 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 136 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 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 38 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 76 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 152 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 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 12 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 24 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 48 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 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 12 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 24 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 48 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 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 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 8 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 8 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 8 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 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 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)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%I64 = call {i64, i1} @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
%V2I64 = call {<2 x i64>, <2 x i1>} @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call {<4 x i64>, <4 x i1>} @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call {<8 x i64>, <8 x i1>} @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call {i32, i1} @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
%V4I32 = call {<4 x i32>, <4 x i1>} @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call {<8 x i32>, <8 x i1>} @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call {<16 x i32>, <16 x i1>} @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call {i16, i1} @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
%V8I16 = call {<8 x i16>, <8 x i1>} @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call {<16 x i16>, <16 x i1>} @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call {<32 x i16>, <32 x i1>} @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call {i8, i1} @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
%V16I8 = call {<16 x i8>, <16 x i1>} @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call {<32 x i8>, <32 x i1>} @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call {<64 x i8>, <64 x i1>} @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
declare {i64, i1} @llvm.umul.with.overflow.i64(i64, i64)
declare {<2 x i64>, <2 x i1>} @llvm.umul.with.overflow.v2i64(<2 x i64>, <2 x i64>)
declare {<4 x i64>, <4 x i1>} @llvm.umul.with.overflow.v4i64(<4 x i64>, <4 x i64>)
declare {<8 x i64>, <8 x i1>} @llvm.umul.with.overflow.v8i64(<8 x i64>, <8 x i64>)
declare {i32, i1} @llvm.umul.with.overflow.i32(i32, i32)
declare {<4 x i32>, <4 x i1>} @llvm.umul.with.overflow.v4i32(<4 x i32>, <4 x i32>)
declare {<8 x i32>, <8 x i1>} @llvm.umul.with.overflow.v8i32(<8 x i32>, <8 x i32>)
declare {<16 x i32>, <16 x i1>} @llvm.umul.with.overflow.v16i32(<16 x i32>, <16 x i32>)
declare {i16, i1} @llvm.umul.with.overflow.i16(i16, i16)
declare {<8 x i16>, <8 x i1>} @llvm.umul.with.overflow.v8i16(<8 x i16>, <8 x i16>)
declare {<16 x i16>, <16 x i1>} @llvm.umul.with.overflow.v16i16(<16 x i16>, <16 x i16>)
declare {<32 x i16>, <32 x i1>} @llvm.umul.with.overflow.v32i16(<32 x i16>, <32 x i16>)
declare {i8, i1} @llvm.umul.with.overflow.i8(i8, i8)
declare {<16 x i8>, <16 x i1>} @llvm.umul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
declare {<32 x i8>, <32 x i1>} @llvm.umul.with.overflow.v32i8(<32 x i8>, <32 x i8>)
declare {<64 x i8>, <64 x i1>} @llvm.umul.with.overflow.v64i8(<64 x i8>, <64 x i8>)
define i32 @umul(i32 %arg) {
; RECIP-LABEL: 'umul'
; 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 33 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 66 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 132 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 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 37 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 74 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 148 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 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 11 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 22 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 44 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 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 11 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 22 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 44 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 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 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 7 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 7 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 7 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 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 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)
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
;
%I64 = call {i64, i1} @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
%V2I64 = call {<2 x i64>, <2 x i1>} @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
%V4I64 = call {<4 x i64>, <4 x i1>} @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
%V8I64 = call {<8 x i64>, <8 x i1>} @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
%I32 = call {i32, i1} @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
%V4I32 = call {<4 x i32>, <4 x i1>} @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
%V8I32 = call {<8 x i32>, <8 x i1>} @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
%V16I32 = call {<16 x i32>, <16 x i1>} @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
%I16 = call {i16, i1} @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
%V8I16 = call {<8 x i16>, <8 x i1>} @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
%V16I16 = call {<16 x i16>, <16 x i1>} @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
%V32I16 = call {<32 x i16>, <32 x i1>} @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
%I8 = call {i8, i1} @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
%V16I8 = call {<16 x i8>, <16 x i1>} @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
%V32I8 = call {<32 x i8>, <32 x i1>} @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
%V64I8 = call {<64 x i8>, <64 x i1>} @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
ret i32 undef
}
Reference in New Issue View Git Blame Copy Permalink