29eb3dcfe6
Summary: Some constants can be handled with less instructions than our current results. And it seems our original approach is not very easy to extend. Therefore this patch proposes to materialize all 64-bit constants by enumerated patterns. I traversed almost all constants to verified the functionality of these pattens. A traversed comparison of the number of instructions used by the original method and the new method has also been completed, where no degradation was caused by this patch. This patch also passed Bootstrap test and SPEC test. Improvements of this patch are shown in llvm/test/CodeGen/PowerPC/constants-i64.ll Reviewed By: steven.zhang, stefanp Differential Revision: https://reviews.llvm.org/D92089
74 lines
2.8 KiB
LLVM
74 lines
2.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -O0 -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
|
|
; RUN: -fast-isel -mcpu=pwr10 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | \
|
|
; RUN: FileCheck %s
|
|
|
|
%struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
|
|
%struct._IO_marker = type { %struct._IO_marker*, %struct._IO_FILE*, i32 }
|
|
|
|
@.str = private unnamed_addr constant [25 x i8] c"Breaking the TOC for FP\0A\00", align 1
|
|
@.str.1 = private unnamed_addr constant [25 x i8] c"Breaking the TOC for GV\0A\00", align 1
|
|
@stdout = external global %struct._IO_FILE*, align 8
|
|
|
|
; Function Attrs: noinline nounwind optnone
|
|
define internal void @loadFP(double* %d) #0 {
|
|
; CHECK-LABEL: loadFP:
|
|
; CHECK: .localentry loadFP, 1
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: mflr r0
|
|
; CHECK-NEXT: std r0, 16(r1)
|
|
; CHECK-NEXT: stdu r1, -112(r1)
|
|
; CHECK-NEXT: std r3, 104(r1)
|
|
; CHECK-NEXT: paddi r3, 0, .L.str@PCREL, 1
|
|
; CHECK-NEXT: bl printf@notoc
|
|
; CHECK-NEXT: ld r4, 104(r1)
|
|
; CHECK-NEXT: lis r3, 8201
|
|
; CHECK-NEXT: ori r3, r3, 64225
|
|
; CHECK-NEXT: rldic r3, r3, 33, 1
|
|
; CHECK-NEXT: oris r3, r3, 36700
|
|
; CHECK-NEXT: ori r3, r3, 10486
|
|
; CHECK-NEXT: std r3, 0(r4)
|
|
; CHECK-NEXT: addi r1, r1, 112
|
|
; CHECK-NEXT: ld r0, 16(r1)
|
|
; CHECK-NEXT: mtlr r0
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%d.addr = alloca double*, align 8
|
|
store double* %d, double** %d.addr, align 8
|
|
%call = call signext i32 (i8*, ...) @printf(i8* getelementptr inbounds ([25 x i8], [25 x i8]* @.str, i64 0, i64 0))
|
|
%0 = load double*, double** %d.addr, align 8
|
|
store double 4.990000e+00, double* %0, align 8
|
|
ret void
|
|
}
|
|
|
|
declare signext i32 @printf(i8*, ...)
|
|
|
|
; Function Attrs: noinline nounwind optnone
|
|
define internal void @loadGV() #0 {
|
|
; CHECK-LABEL: loadGV:
|
|
; CHECK: .localentry loadGV, 1
|
|
; CHECK-NEXT: # %bb.0: # %entry
|
|
; CHECK-NEXT: mflr r0
|
|
; CHECK-NEXT: std r0, 16(r1)
|
|
; CHECK-NEXT: stdu r1, -96(r1)
|
|
; CHECK-NEXT: paddi r3, 0, .L.str.1@PCREL, 1
|
|
; CHECK-NEXT: bl printf@notoc
|
|
; CHECK-NEXT: pld r3, stdout@got@pcrel(0), 1
|
|
; CHECK-NEXT: ld r4, 0(r3)
|
|
; CHECK-NEXT: li r3, 97
|
|
; CHECK-NEXT: bl _IO_putc@notoc
|
|
; CHECK-NEXT: addi r1, r1, 96
|
|
; CHECK-NEXT: ld r0, 16(r1)
|
|
; CHECK-NEXT: mtlr r0
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%call = call signext i32 (i8*, ...) @printf(i8* getelementptr inbounds ([25 x i8], [25 x i8]* @.str.1, i64 0, i64 0))
|
|
%0 = load %struct._IO_FILE*, %struct._IO_FILE** @stdout, align 8
|
|
%call1 = call signext i32 @_IO_putc(i32 signext 97, %struct._IO_FILE* %0)
|
|
ret void
|
|
}
|
|
|
|
declare signext i32 @_IO_putc(i32 signext, %struct._IO_FILE*)
|
|
|
|
attributes #0 = { noinline nounwind optnone }
|