1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
llvm-mirror/test/CodeGen/X86/sse42-intrinsics-x86_64.ll
Simon Pilgrim d654e7d40c [X86] Handle COPYs of physregs better (regalloc hints)
Enable enableMultipleCopyHints() on X86.

Original Patch by @jonpa:

While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling.

Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates.

Differential Revision: https://reviews.llvm.org/D38128

llvm-svn: 342578
2018-09-19 18:59:08 +00:00

29 lines
1.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=-avx,+sse4.2 -show-mc-encoding | FileCheck %s --check-prefixes=CHECK,SSE
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx -show-mc-encoding | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f,+avx512bw,+avx512dq,+avx512vl -show-mc-encoding | FileCheck %s --check-prefixes=CHECK,AVX,AVX512
declare i64 @llvm.x86.sse42.crc32.64.8(i64, i8) nounwind
declare i64 @llvm.x86.sse42.crc32.64.64(i64, i64) nounwind
define i64 @crc32_64_8(i64 %a, i8 %b) nounwind {
; CHECK-LABEL: crc32_64_8:
; CHECK: ## %bb.0:
; CHECK-NEXT: movq %rdi, %rax ## encoding: [0x48,0x89,0xf8]
; CHECK-NEXT: crc32b %sil, %eax ## encoding: [0xf2,0x40,0x0f,0x38,0xf0,0xc6]
; CHECK-NEXT: retq ## encoding: [0xc3]
%tmp = call i64 @llvm.x86.sse42.crc32.64.8(i64 %a, i8 %b)
ret i64 %tmp
}
define i64 @crc32_64_64(i64 %a, i64 %b) nounwind {
; CHECK-LABEL: crc32_64_64:
; CHECK: ## %bb.0:
; CHECK-NEXT: movq %rdi, %rax ## encoding: [0x48,0x89,0xf8]
; CHECK-NEXT: crc32q %rsi, %rax ## encoding: [0xf2,0x48,0x0f,0x38,0xf1,0xc6]
; CHECK-NEXT: retq ## encoding: [0xc3]
%tmp = call i64 @llvm.x86.sse42.crc32.64.64(i64 %a, i64 %b)
ret i64 %tmp
}