mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
74c92ba816
The concept of G_GLOBAL_VALUE is nice and simple, but always using it as the representation for global var addressing until selection time creates some problems in optimizing accesses in certain code/relocation models. The problem comes from trying to optimize adrp -> add -> load/store sequences in the most common "small" code model. These accesses can be optimized into an adrp -> load with the add offset being folded into the load's immediate field. If we try to keep all global var references as a single generic instruction then by the time we get to the complex operand trying to match these, we end up generating an adrp at the point of use. The real issue here is that we don't have any form of CSE during selection, so the code size will bloat from many redundant adrp's. This patch custom legalizes small code mode non-GOT G_GLOBALs into target ADRP and a new "target specific generic opcode" G_ADD_LOW. We also teach the localizer to localize these instructions via the custom hook that was added recently. Finally, the complex pattern for indexed loads/stores is extended to try to fold these G_ADD_LOW instructions into the load immediate. On -O0 CTMark, we see a 0.8% geomean code size improvement. We should also see some minor performance improvements too. Differential Revision: https://reviews.llvm.org/D78465
62 lines
1.5 KiB
LLVM
62 lines
1.5 KiB
LLVM
; RUN: llc -mtriple aarch64-unknown-windows-msvc -filetype asm -o - %s | FileCheck %s -check-prefixes=CHECK,DAG-ISEL
|
|
; RUN: llc -mtriple aarch64-unknown-windows-msvc -fast-isel -filetype asm -o - %s | FileCheck %s -check-prefixes=CHECK,FAST-ISEL
|
|
; RUN: llc -mtriple aarch64-unknown-windows-msvc -verify-machineinstrs -O0 -filetype asm -o - %s | FileCheck %s -check-prefixes=CHECK,GLOBAL-ISEL,GLOBAL-ISEL-FALLBACK
|
|
|
|
@var = external dllimport global i32
|
|
@ext = external global i32
|
|
declare dllimport i32 @external()
|
|
declare i32 @internal()
|
|
|
|
define i32 @get_var() {
|
|
%1 = load i32, i32* @var, align 4
|
|
ret i32 %1
|
|
}
|
|
|
|
; CHECK-LABEL: get_var
|
|
; CHECK: adrp x8, __imp_var
|
|
; CHECK: ldr x8, [x8, __imp_var]
|
|
; CHECK: ldr w0, [x8]
|
|
; CHECK: ret
|
|
|
|
define i32 @get_ext() {
|
|
%1 = load i32, i32* @ext, align 4
|
|
ret i32 %1
|
|
}
|
|
|
|
; CHECK-LABEL: get_ext
|
|
; CHECK: adrp x8, ext
|
|
; DAG-ISEL: ldr w0, [x8, ext]
|
|
; FAST-ISEL: add x8, x8, ext
|
|
; FAST-ISEL: ldr w0, [x8]
|
|
; GLOBAL-ISEL-FALLBACK: ldr w0, [x8, ext]
|
|
; CHECK: ret
|
|
|
|
define i32* @get_var_pointer() {
|
|
ret i32* @var
|
|
}
|
|
|
|
; CHECK-LABEL: get_var_pointer
|
|
; CHECK: adrp [[REG1:x[0-9]+]], __imp_var
|
|
; CHECK: ldr {{x[0-9]+}}, {{\[}}[[REG1]], __imp_var]
|
|
; CHECK: ret
|
|
|
|
define i32 @call_external() {
|
|
%call = tail call i32 @external()
|
|
ret i32 %call
|
|
}
|
|
|
|
; CHECK-LABEL: call_external
|
|
; CHECK: adrp x0, __imp_external
|
|
; CHECK: ldr x0, [x0, __imp_external]
|
|
; CHECK: br x0
|
|
|
|
define i32 @call_internal() {
|
|
%call = tail call i32 @internal()
|
|
ret i32 %call
|
|
}
|
|
|
|
; CHECK-LABEL: call_internal
|
|
; DAG-ISEL: b internal
|
|
; FAST-ISEL: b internal
|
|
; GLOBAL-ISEL: b internal
|