diff options
Diffstat (limited to 'test/CodeGen/R600/llvm.sqrt.ll')
| -rw-r--r-- | test/CodeGen/R600/llvm.sqrt.ll | 59 |
1 files changed, 30 insertions, 29 deletions
diff --git a/test/CodeGen/R600/llvm.sqrt.ll b/test/CodeGen/R600/llvm.sqrt.ll index c039225..cc4717a 100644 --- a/test/CodeGen/R600/llvm.sqrt.ll +++ b/test/CodeGen/R600/llvm.sqrt.ll @@ -1,11 +1,12 @@ -; RUN: llc < %s -march=r600 --mcpu=redwood | FileCheck %s --check-prefix=R600-CHECK -; RUN: llc < %s -march=r600 --mcpu=SI -verify-machineinstrs| FileCheck %s --check-prefix=SI-CHECK +; RUN: llc < %s -march=r600 --mcpu=redwood | FileCheck %s --check-prefix=R600 +; RUN: llc < %s -march=amdgcn --mcpu=SI -verify-machineinstrs| FileCheck %s --check-prefix=SI +; RUN: llc < %s -march=amdgcn --mcpu=tonga -verify-machineinstrs| FileCheck %s --check-prefix=SI -; R600-CHECK-LABEL: {{^}}sqrt_f32: -; R600-CHECK: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[2].Z -; R600-CHECK: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[2].Z, PS -; SI-CHECK-LABEL: {{^}}sqrt_f32: -; SI-CHECK: v_sqrt_f32_e32 +; R600-LABEL: {{^}}sqrt_f32: +; R600: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[2].Z +; R600: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[2].Z, PS +; SI-LABEL: {{^}}sqrt_f32: +; SI: v_sqrt_f32_e32 define void @sqrt_f32(float addrspace(1)* %out, float %in) { entry: %0 = call float @llvm.sqrt.f32(float %in) @@ -13,14 +14,14 @@ entry: ret void } -; R600-CHECK-LABEL: {{^}}sqrt_v2f32: -; R600-CHECK-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[2].W -; R600-CHECK-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[2].W, PS -; R600-CHECK-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].X -; R600-CHECK-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].X, PS -; SI-CHECK-LABEL: {{^}}sqrt_v2f32: -; SI-CHECK: v_sqrt_f32_e32 -; SI-CHECK: v_sqrt_f32_e32 +; R600-LABEL: {{^}}sqrt_v2f32: +; R600-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[2].W +; R600-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[2].W, PS +; R600-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].X +; R600-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].X, PS +; SI-LABEL: {{^}}sqrt_v2f32: +; SI: v_sqrt_f32_e32 +; SI: v_sqrt_f32_e32 define void @sqrt_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) { entry: %0 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> %in) @@ -28,20 +29,20 @@ entry: ret void } -; R600-CHECK-LABEL: {{^}}sqrt_v4f32: -; R600-CHECK-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].Y -; R600-CHECK-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].Y, PS -; R600-CHECK-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].Z -; R600-CHECK-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].Z, PS -; R600-CHECK-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].W -; R600-CHECK-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].W, PS -; R600-CHECK-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[4].X -; R600-CHECK-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[4].X, PS -; SI-CHECK-LABEL: {{^}}sqrt_v4f32: -; SI-CHECK: v_sqrt_f32_e32 -; SI-CHECK: v_sqrt_f32_e32 -; SI-CHECK: v_sqrt_f32_e32 -; SI-CHECK: v_sqrt_f32_e32 +; R600-LABEL: {{^}}sqrt_v4f32: +; R600-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].Y +; R600-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].Y, PS +; R600-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].Z +; R600-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].Z, PS +; R600-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[3].W +; R600-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[3].W, PS +; R600-DAG: RECIPSQRT_CLAMPED * T{{[0-9]\.[XYZW]}}, KC0[4].X +; R600-DAG: MUL NON-IEEE T{{[0-9]\.[XYZW]}}, KC0[4].X, PS +; SI-LABEL: {{^}}sqrt_v4f32: +; SI: v_sqrt_f32_e32 +; SI: v_sqrt_f32_e32 +; SI: v_sqrt_f32_e32 +; SI: v_sqrt_f32_e32 define void @sqrt_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) { entry: %0 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> %in) |