mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
e2e0a9d886
The default promotion for the add_sat/sub_sat nodes currently does:
ANY_EXTEND iN to iM
SHL by M-N
[US][ADD|SUB]SAT
L/ASHR by M-N
If the promoted add_sat or sub_sat node is not legal, this can produce code
that effectively does a lot of shifting (and requiring large constants to be
materialised) just to use the overflow flag. It is simpler to just do the
saturation manually, using the higher bitwidth addition and a min/max against
the saturating bounds. That is what this patch attempts to do.
Differential Revision: https://reviews.llvm.org/D68926
llvm-svn: 375211
78 lines
2.2 KiB
LLVM
78 lines
2.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=aarch64-- | FileCheck %s
|
|
|
|
declare i4 @llvm.uadd.sat.i4(i4, i4)
|
|
declare i8 @llvm.uadd.sat.i8(i8, i8)
|
|
declare i16 @llvm.uadd.sat.i16(i16, i16)
|
|
declare i32 @llvm.uadd.sat.i32(i32, i32)
|
|
declare i64 @llvm.uadd.sat.i64(i64, i64)
|
|
|
|
define i32 @func32(i32 %x, i32 %y, i32 %z) nounwind {
|
|
; CHECK-LABEL: func32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mul w8, w1, w2
|
|
; CHECK-NEXT: adds w8, w0, w8
|
|
; CHECK-NEXT: csinv w0, w8, wzr, lo
|
|
; CHECK-NEXT: ret
|
|
%a = mul i32 %y, %z
|
|
%tmp = call i32 @llvm.uadd.sat.i32(i32 %x, i32 %a)
|
|
ret i32 %tmp
|
|
}
|
|
|
|
define i64 @func64(i64 %x, i64 %y, i64 %z) nounwind {
|
|
; CHECK-LABEL: func64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: adds x8, x0, x2
|
|
; CHECK-NEXT: csinv x0, x8, xzr, lo
|
|
; CHECK-NEXT: ret
|
|
%a = mul i64 %y, %z
|
|
%tmp = call i64 @llvm.uadd.sat.i64(i64 %x, i64 %z)
|
|
ret i64 %tmp
|
|
}
|
|
|
|
define i16 @func16(i16 %x, i16 %y, i16 %z) nounwind {
|
|
; CHECK-LABEL: func16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and w8, w0, #0xffff
|
|
; CHECK-NEXT: mul w9, w1, w2
|
|
; CHECK-NEXT: add w8, w8, w9, uxth
|
|
; CHECK-NEXT: mov w9, #65535
|
|
; CHECK-NEXT: cmp w8, w9
|
|
; CHECK-NEXT: csel w0, w8, w9, lo
|
|
; CHECK-NEXT: ret
|
|
%a = mul i16 %y, %z
|
|
%tmp = call i16 @llvm.uadd.sat.i16(i16 %x, i16 %a)
|
|
ret i16 %tmp
|
|
}
|
|
|
|
define i8 @func8(i8 %x, i8 %y, i8 %z) nounwind {
|
|
; CHECK-LABEL: func8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and w8, w0, #0xff
|
|
; CHECK-NEXT: mul w9, w1, w2
|
|
; CHECK-NEXT: add w8, w8, w9, uxtb
|
|
; CHECK-NEXT: cmp w8, #255 // =255
|
|
; CHECK-NEXT: mov w9, #255
|
|
; CHECK-NEXT: csel w0, w8, w9, lo
|
|
; CHECK-NEXT: ret
|
|
%a = mul i8 %y, %z
|
|
%tmp = call i8 @llvm.uadd.sat.i8(i8 %x, i8 %a)
|
|
ret i8 %tmp
|
|
}
|
|
|
|
define i4 @func4(i4 %x, i4 %y, i4 %z) nounwind {
|
|
; CHECK-LABEL: func4:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mul w9, w1, w2
|
|
; CHECK-NEXT: and w8, w0, #0xf
|
|
; CHECK-NEXT: and w9, w9, #0xf
|
|
; CHECK-NEXT: add w8, w8, w9
|
|
; CHECK-NEXT: cmp w8, #15 // =15
|
|
; CHECK-NEXT: mov w9, #15
|
|
; CHECK-NEXT: csel w0, w8, w9, lo
|
|
; CHECK-NEXT: ret
|
|
%a = mul i4 %y, %z
|
|
%tmp = call i4 @llvm.uadd.sat.i4(i4 %x, i4 %a)
|
|
ret i4 %tmp
|
|
}
|