diff options
| author | Adhemerval Zanella <adhemerval.zanella@linaro.org> | 2019-03-18 18:45:57 +0000 |
|---|---|---|
| committer | Adhemerval Zanella <adhemerval.zanella@linaro.org> | 2019-03-18 18:45:57 +0000 |
| commit | a3cefa5d6492a4ba593b74b1aa615f00a5b6166d (patch) | |
| tree | d8376cb3cd79b6fb89b4421c0936a5d3337a29ac /llvm/test/CodeGen/AArch64/literal_pools_float.ll | |
| parent | 664c1ef52849623ef509e34968e0807a21b7bf15 (diff) | |
| download | bcm5719-llvm-a3cefa5d6492a4ba593b74b1aa615f00a5b6166d.tar.gz bcm5719-llvm-a3cefa5d6492a4ba593b74b1aa615f00a5b6166d.zip | |
[AArch64] Optimize floating point materialization
This patch follows some ideas from r352866 to optimize the floating
point materialization even further. It changes isFPImmLegal to
considere up to 2 mov instruction or up to 5 in case subtarget has
fused literals.
The rationale is the cost is the same for mov+fmov vs. adrp+ldr; but
the mov+fmov sequence is always better because of the reduced d-cache
pressure. The timings are still the same if you consider movw+movk+fmov
vs. adrp+ldr will be fused (although one instruction longer).
Reviewers: efriedma
Differential Revision: https://reviews.llvm.org/D58460
llvm-svn: 356390
Diffstat (limited to 'llvm/test/CodeGen/AArch64/literal_pools_float.ll')
| -rw-r--r-- | llvm/test/CodeGen/AArch64/literal_pools_float.ll | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/llvm/test/CodeGen/AArch64/literal_pools_float.ll b/llvm/test/CodeGen/AArch64/literal_pools_float.ll index 1a673949d7f..4031e072f1f 100644 --- a/llvm/test/CodeGen/AArch64/literal_pools_float.ll +++ b/llvm/test/CodeGen/AArch64/literal_pools_float.ll @@ -31,16 +31,19 @@ define void @floating_lits() { %doubleval = load double, double* @vardouble %newdouble = fadd double %doubleval, 129.0 -; CHECK: adrp x[[LITBASE:[0-9]+]], [[CURLIT:.LCPI[0-9]+_[0-9]+]] -; CHECK: ldr [[LIT129:d[0-9]+]], [x[[LITBASE]], {{#?}}:lo12:[[CURLIT]]] ; CHECK-NOFP-NOT: ldr {{d[0-9]+}}, +; CHECK: mov [[W129:x[0-9]+]], #35184372088832 +; CHECK: movk [[W129]], #16480, lsl #48 +; CHECK: fmov {{d[0-9]+}}, [[W129]] ; CHECK-NOFP-NOT: fadd -; CHECK-TINY: ldr [[LIT129:d[0-9]+]], [[CURLIT:.LCPI[0-9]+_[0-9]+]] +; CHECK-TINY: mov [[W129:x[0-9]+]], #35184372088832 +; CHECK-TINY: movk [[W129]], #16480, lsl #48 +; CHECK-TINY: fmov {{d[0-9]+}}, [[W129]] ; CHECK-NOFP-TINY-NOT: ldr {{d[0-9]+}}, ; CHECK-NOFP-TINY-NOT: fadd -; CHECK-LARGE: movz x[[LITADDR:[0-9]+]], #:abs_g0_nc:[[CURLIT:.LCPI[0-9]+_[0-9]+]] +; CHECK-LARGE: movz x[[LITADDR:[0-9]+]], #:abs_g0_nc:[[CURLIT:vardouble]] ; CHECK-LARGE: movk x[[LITADDR]], #:abs_g1_nc:[[CURLIT]] ; CHECK-LARGE: movk x[[LITADDR]], #:abs_g2_nc:[[CURLIT]] ; CHECK-LARGE: movk x[[LITADDR]], #:abs_g3:[[CURLIT]] |
