diff options
Diffstat (limited to 'test/CodeGen/R600/ffloor.f64.ll')
-rw-r--r-- | test/CodeGen/R600/ffloor.f64.ll | 63 |
1 files changed, 42 insertions, 21 deletions
diff --git a/test/CodeGen/R600/ffloor.f64.ll b/test/CodeGen/R600/ffloor.f64.ll index 745ad3b..45f8382 100644 --- a/test/CodeGen/R600/ffloor.f64.ll +++ b/test/CodeGen/R600/ffloor.f64.ll @@ -1,7 +1,8 @@ -; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s -; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s -; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s +declare double @llvm.fabs.f64(double %Val) declare double @llvm.floor.f64(double) nounwind readnone declare <2 x double> @llvm.floor.v2f64(<2 x double>) nounwind readnone declare <3 x double> @llvm.floor.v3f64(<3 x double>) nounwind readnone @@ -11,24 +12,11 @@ declare <16 x double> @llvm.floor.v16f64(<16 x double>) nounwind readnone ; FUNC-LABEL: {{^}}ffloor_f64: ; CI: v_floor_f64_e32 - -; SI: s_bfe_u32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014 -; SI: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000 -; SI: s_add_i32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01 -; SI: s_lshr_b64 -; SI: s_not_b64 -; SI: s_and_b64 -; SI: cmp_lt_i32 -; SI: cndmask_b32 -; SI: cndmask_b32 -; SI: cmp_gt_i32 -; SI: cndmask_b32 -; SI: cndmask_b32 -; SI-DAG: v_cmp_lt_f64 -; SI-DAG: v_cmp_lg_f64 -; SI-DAG: s_and_b64 -; SI-DAG: v_cndmask_b32 -; SI-DAG: v_cndmask_b32 +; SI: v_fract_f64_e32 +; SI: v_min_f64 +; SI: v_cmp_class_f64_e64 +; SI: v_cndmask_b32_e64 +; SI: v_cndmask_b32_e64 ; SI: v_add_f64 ; SI: s_endpgm define void @ffloor_f64(double addrspace(1)* %out, double %x) { @@ -37,6 +25,39 @@ define void @ffloor_f64(double addrspace(1)* %out, double %x) { ret void } +; FUNC-LABEL: {{^}}ffloor_f64_neg: +; CI: v_floor_f64_e64 +; SI: v_fract_f64_e64 {{v[[0-9]+:[0-9]+]}}, -[[INPUT:s[[0-9]+:[0-9]+]]] +; SI: v_min_f64 +; SI: v_cmp_class_f64_e64 +; SI: v_cndmask_b32_e64 +; SI: v_cndmask_b32_e64 +; SI: v_add_f64 {{v[[0-9]+:[0-9]+]}}, -[[INPUT]] +; SI: s_endpgm +define void @ffloor_f64_neg(double addrspace(1)* %out, double %x) { + %neg = fsub double 0.0, %x + %y = call double @llvm.floor.f64(double %neg) nounwind readnone + store double %y, double addrspace(1)* %out + ret void +} + +; FUNC-LABEL: {{^}}ffloor_f64_neg_abs: +; CI: v_floor_f64_e64 +; SI: v_fract_f64_e64 {{v[[0-9]+:[0-9]+]}}, -|[[INPUT:s[[0-9]+:[0-9]+]]]| +; SI: v_min_f64 +; SI: v_cmp_class_f64_e64 +; SI: v_cndmask_b32_e64 +; SI: v_cndmask_b32_e64 +; SI: v_add_f64 {{v[[0-9]+:[0-9]+]}}, -|[[INPUT]]| +; SI: s_endpgm +define void @ffloor_f64_neg_abs(double addrspace(1)* %out, double %x) { + %abs = call double @llvm.fabs.f64(double %x) + %neg = fsub double 0.0, %abs + %y = call double @llvm.floor.f64(double %neg) nounwind readnone + store double %y, double addrspace(1)* %out + ret void +} + ; FUNC-LABEL: {{^}}ffloor_v2f64: ; CI: v_floor_f64_e32 ; CI: v_floor_f64_e32 |