mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
2f3d552ba6
This is the last one in a series of patches to support better code generation for bitfield insert.
BitPermutationSelector already support ISD::ZERO_EXTEND but not TRUNCATE.
This patch adds support for ISD:TRUNCATE in BitPermutationSelector.
For example of this test case,
struct s64b {
int a:4;
int b:16;
int c:24;
};
void bitfieldinsert64b(struct s64b *p, unsigned char v) {
p->b = v;
}
the selection DAG loos like:
t14: i32,ch = load<(load 4 from %ir.0)> t0, t2, undef:i64
t18: i32 = and t14, Constant:i32<-1048561>
t4: i64,ch = CopyFromReg t0, Register:i64 %1
t22: i64 = AssertZext t4, ValueType:ch:i8
t23: i32 = truncate t22
t16: i32 = shl nuw nsw t23, Constant:i32<4>
t19: i32 = or t18, t16
t20: ch = store<(store 4 into %ir.0)> t14:1, t19, t2, undef:i64
By handling truncate in the BitPermutationSelector, we can use information from AssertZext when selecting t19 and skip the mask operation corresponding to t18.
So the generated sequences with and without this patch are
without this patch
rlwinm 5, 5, 0, 28, 11 # corresponding to t18
rlwimi 5, 4, 4, 20, 27
with this patch
rlwimi 5, 4, 4, 12, 27
Differential Revision: https://reviews.llvm.org/D49076
llvm-svn: 350118
121 lines
3.2 KiB
LLVM
121 lines
3.2 KiB
LLVM
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 < %s | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 < %s | FileCheck %s
|
|
|
|
; equivalent C code
|
|
; struct s64 {
|
|
; int a:5;
|
|
; int b:16;
|
|
; long c:42;
|
|
; };
|
|
; void bitfieldinsert64(struct s *p, unsigned short v) {
|
|
; p->b = v;
|
|
; }
|
|
|
|
%struct.s64 = type { i64 }
|
|
|
|
define void @bitfieldinsert64(%struct.s64* nocapture %p, i16 zeroext %v) {
|
|
; CHECK-LABEL: @bitfieldinsert64
|
|
; CHECK: ld [[REG1:[0-9]+]], 0(3)
|
|
; CHECK-NEXT: rlwimi [[REG1]], 4, 5, 11, 26
|
|
; CHECK-NEXT: std [[REG1]], 0(3)
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%0 = getelementptr inbounds %struct.s64, %struct.s64* %p, i64 0, i32 0
|
|
%1 = zext i16 %v to i64
|
|
%bf.load = load i64, i64* %0, align 8
|
|
%bf.shl = shl nuw nsw i64 %1, 5
|
|
%bf.clear = and i64 %bf.load, -2097121
|
|
%bf.set = or i64 %bf.clear, %bf.shl
|
|
store i64 %bf.set, i64* %0, align 8
|
|
ret void
|
|
}
|
|
|
|
; bitfieldinsert32: Test for rlwimi
|
|
; equivalent C code
|
|
; struct s32 {
|
|
; int a:8;
|
|
; int b:16;
|
|
; int c:8;
|
|
; };
|
|
; void bitfieldinsert32(struct s32 *p, unsigned int v) {
|
|
; p->b = v;
|
|
; }
|
|
|
|
%struct.s32 = type { i32 }
|
|
|
|
define void @bitfieldinsert32(%struct.s32* nocapture %p, i32 zeroext %v) {
|
|
; CHECK-LABEL: @bitfieldinsert32
|
|
; CHECK: lwz [[REG1:[0-9]+]], 0(3)
|
|
; CHECK-NEXT: rlwimi [[REG1]], 4, 8, 8, 23
|
|
; CHECK-NEXT: stw [[REG1]], 0(3)
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%0 = getelementptr inbounds %struct.s32, %struct.s32* %p, i64 0, i32 0
|
|
%bf.load = load i32, i32* %0, align 4
|
|
%bf.value = shl i32 %v, 8
|
|
%bf.shl = and i32 %bf.value, 16776960
|
|
%bf.clear = and i32 %bf.load, -16776961
|
|
%bf.set = or i32 %bf.clear, %bf.shl
|
|
store i32 %bf.set, i32* %0, align 4
|
|
ret void
|
|
}
|
|
|
|
; test cases which include ISD::TRUNCATE
|
|
; equivalent C code
|
|
; struct s64b {
|
|
; int a:4;
|
|
; int b:16;
|
|
; int c:24;
|
|
; };
|
|
; void bitfieldinsert64b(struct s64b *p, unsigned char v) {
|
|
; p->b = v;
|
|
; }
|
|
|
|
%struct.s64b = type { i24, i24 }
|
|
|
|
define void @bitfieldinsert64b(%struct.s64b* nocapture %p, i8 zeroext %v) {
|
|
; CHECK-LABEL: @bitfieldinsert64b
|
|
; CHECK: lwz [[REG1:[0-9]+]], 0(3)
|
|
; CHECK-NEXT: rlwimi [[REG1]], 4, 4, 12, 27
|
|
; CHECK-NEXT: stw [[REG1]], 0(3)
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%conv = zext i8 %v to i32
|
|
%0 = bitcast %struct.s64b* %p to i32*
|
|
%bf.load = load i32, i32* %0, align 4
|
|
%bf.shl = shl nuw nsw i32 %conv, 4
|
|
%bf.clear = and i32 %bf.load, -1048561
|
|
%bf.set = or i32 %bf.clear, %bf.shl
|
|
store i32 %bf.set, i32* %0, align 4
|
|
ret void
|
|
}
|
|
|
|
; equivalent C code
|
|
; struct s64c {
|
|
; int a:5;
|
|
; int b:16;
|
|
; long c:10;
|
|
; };
|
|
; void bitfieldinsert64c(struct s64c *p, unsigned short v) {
|
|
; p->b = v;
|
|
; }
|
|
|
|
%struct.s64c = type { i32, [4 x i8] }
|
|
|
|
define void @bitfieldinsert64c(%struct.s64c* nocapture %p, i16 zeroext %v) {
|
|
; CHECK-LABEL: @bitfieldinsert64c
|
|
; CHECK: lwz [[REG1:[0-9]+]], 0(3)
|
|
; CHECK-NEXT: rlwimi [[REG1]], 4, 5, 11, 26
|
|
; CHECK-NEXT: stw [[REG1]], 0(3)
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%conv = zext i16 %v to i32
|
|
%0 = getelementptr inbounds %struct.s64c, %struct.s64c* %p, i64 0, i32 0
|
|
%bf.load = load i32, i32* %0, align 8
|
|
%bf.shl = shl nuw nsw i32 %conv, 5
|
|
%bf.clear = and i32 %bf.load, -2097121
|
|
%bf.set = or i32 %bf.clear, %bf.shl
|
|
store i32 %bf.set, i32* %0, align 8
|
|
ret void
|
|
}
|