e03ba2198d
These expansions were rather inefficient and were done with more code than necessary. This change optimizes them to use expansions more similar to GCC. The code size is the same (when optimizing for code size) but somehow LLVM reorders blocks in a non-optimal way. Still, this should be an improvement with a reduction in code size of around 0.12% (when building compiler-rt). Differential Revision: https://reviews.llvm.org/D86418
53 lines
1.3 KiB
LLVM
53 lines
1.3 KiB
LLVM
; RUN: llc < %s -march=avr | FileCheck %s
|
|
|
|
; Optimize for speed.
|
|
; CHECK-LABEL: shift_i8_i8_speed
|
|
define i8 @shift_i8_i8_speed(i8 %a, i8 %b) {
|
|
; CHECK: dec r22
|
|
; CHECK-NEXT: brmi .LBB0_2
|
|
; CHECK-NEXT: .LBB0_1:
|
|
; CHECK-NEXT: lsl r24
|
|
; CHECK-NEXT: dec r22
|
|
; CHECK-NEXT: brpl .LBB0_1
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: ret
|
|
%result = shl i8 %a, %b
|
|
ret i8 %result
|
|
}
|
|
|
|
; Optimize for size (producing slightly smaller code).
|
|
; CHECK-LABEL: shift_i8_i8_size
|
|
define i8 @shift_i8_i8_size(i8 %a, i8 %b) optsize {
|
|
; CHECK: .LBB1_1:
|
|
; CHECK-NEXT: dec r22
|
|
; CHECK-NEXT: brmi .LBB1_3
|
|
; CHECK: lsl r24
|
|
; CHECK-NEXT: rjmp .LBB1_1
|
|
; CHECK-NEXT: .LBB1_3:
|
|
; CHECK-NEXT: ret
|
|
%result = shl i8 %a, %b
|
|
ret i8 %result
|
|
}
|
|
|
|
; CHECK-LABEL: shift_i16_i16
|
|
define i16 @shift_i16_i16(i16 %a, i16 %b) {
|
|
; CHECK: dec r22
|
|
; CHECK-NEXT: brmi .LBB2_2
|
|
; CHECK-NEXT: .LBB2_1:
|
|
; CHECK-NEXT: lsl r24
|
|
; CHECK-NEXT: rol r25
|
|
; CHECK-NEXT: dec r22
|
|
; CHECK-NEXT: brpl .LBB2_1
|
|
; CHECK-NEXT: .LBB2_2:
|
|
; CHECK-NEXT: ret
|
|
%result = shl i16 %a, %b
|
|
ret i16 %result
|
|
}
|
|
|
|
; CHECK-LABEL: shift_i64_i64
|
|
define i64 @shift_i64_i64(i64 %a, i64 %b) {
|
|
; CHECK: call __ashldi3
|
|
%result = shl i64 %a, %b
|
|
ret i64 %result
|
|
}
|