diff options
Diffstat (limited to 'clang/test/CodeGen/aarch64-neon-fma.c')
| -rw-r--r-- | clang/test/CodeGen/aarch64-neon-fma.c | 23 |
1 files changed, 13 insertions, 10 deletions
diff --git a/clang/test/CodeGen/aarch64-neon-fma.c b/clang/test/CodeGen/aarch64-neon-fma.c index 8126fb21da7..ac808333365 100644 --- a/clang/test/CodeGen/aarch64-neon-fma.c +++ b/clang/test/CodeGen/aarch64-neon-fma.c @@ -1,8 +1,5 @@ // REQUIRES: aarch64-registered-target -// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -S -O3 \ -// RUN: -ffp-contract=off -o - %s | FileCheck %s -// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -S -O3 \ -// RUN: -o - %s | FileCheck -check-prefix=CHECK-FMA %s +// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -S -O3 -o - %s | FileCheck %s // Test new aarch64 intrinsics and types @@ -13,7 +10,8 @@ float32x2_t test_vmla_n_f32(float32x2_t a, float32x2_t b, float32_t c) { return vmla_n_f32(a, b, c); // CHECK: fmul {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0] // CHECK: fadd {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s - // CHECK-FMA: fmla {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0] + // CHECK-FMA: dup {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0] + // CHECK-FMA: fmla {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s } float32x4_t test_vmlaq_n_f32(float32x4_t a, float32x4_t b, float32_t c) { @@ -21,7 +19,8 @@ float32x4_t test_vmlaq_n_f32(float32x4_t a, float32x4_t b, float32_t c) { return vmlaq_n_f32(a, b, c); // CHECK: fmul {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0] // CHECK: fadd {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s - // CHECK-FMA: fmla {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0] + // CHECK-FMA: dup {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0] + // CHECK-FMA: fmla {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s } float64x2_t test_vmlaq_n_f64(float64x2_t a, float64x2_t b, float64_t c) { @@ -29,7 +28,8 @@ float64x2_t test_vmlaq_n_f64(float64x2_t a, float64x2_t b, float64_t c) { return vmlaq_n_f64(a, b, c); // CHECK: fmul {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0] // CHECK: fadd {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d - // CHECK-FMA: fmla {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0] + // CHECK-FMA: dup {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0] + // CHECK-FMA: fmla {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d } float32x4_t test_vmlsq_n_f32(float32x4_t a, float32x4_t b, float32_t c) { @@ -37,7 +37,8 @@ float32x4_t test_vmlsq_n_f32(float32x4_t a, float32x4_t b, float32_t c) { return vmlsq_n_f32(a, b, c); // CHECK: fmul {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0] // CHECK: fsub {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s - // CHECK-FMA: fmls {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0] + // CHECK-FMA: dup {{v[0-9]+}}.4s, {{v[0-9]+}}.s[0] + // CHECK-FMA: fmls {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s } float32x2_t test_vmls_n_f32(float32x2_t a, float32x2_t b, float32_t c) { @@ -45,7 +46,8 @@ float32x2_t test_vmls_n_f32(float32x2_t a, float32x2_t b, float32_t c) { return vmls_n_f32(a, b, c); // CHECK: fmul {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0] // CHECK: fsub {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s - // CHECK-FMA: fmls {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0] + // CHECK-FMA: dup {{v[0-9]+}}.2s, {{v[0-9]+}}.s[0] + // CHECK-FMA: fmls {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s } float64x2_t test_vmlsq_n_f64(float64x2_t a, float64x2_t b, float64_t c) { @@ -53,7 +55,8 @@ float64x2_t test_vmlsq_n_f64(float64x2_t a, float64x2_t b, float64_t c) { return vmlsq_n_f64(a, b, c); // CHECK: fmul {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0] // CHECK: fsub {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d - // CHECK-FMA: fmls {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0] + // CHECK-FMA: dup {{v[0-9]+}}.2d, {{v[0-9]+}}.d[0] + // CHECK-FMA: fmls {{v[0-9]+}}.2d, {{v[0-9]+}}.2d, {{v[0-9]+}}.2d } float32x2_t test_vmla_lane_f32_0(float32x2_t a, float32x2_t b, float32x2_t v) { |
