| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=X32 |
| ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=X32 |
| ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=X64 |
| ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=X64 |
| |
| define <2 x double> @fabs_v2f64(<2 x double> %p) { |
| ; X32-LABEL: fabs_v2f64: |
| ; X32: # BB#0: |
| ; X32-NEXT: vandpd .LCPI0_0, %xmm0, %xmm0 |
| ; X32-NEXT: retl |
| ; |
| ; X64-LABEL: fabs_v2f64: |
| ; X64: # BB#0: |
| ; X64-NEXT: vandpd {{.*}}(%rip), %xmm0, %xmm0 |
| ; X64-NEXT: retq |
| %t = call <2 x double> @llvm.fabs.v2f64(<2 x double> %p) |
| ret <2 x double> %t |
| } |
| declare <2 x double> @llvm.fabs.v2f64(<2 x double> %p) |
| |
| define <4 x float> @fabs_v4f32(<4 x float> %p) { |
| ; X32-LABEL: fabs_v4f32: |
| ; X32: # BB#0: |
| ; X32-NEXT: vandps .LCPI1_0, %xmm0, %xmm0 |
| ; X32-NEXT: retl |
| ; |
| ; X64-LABEL: fabs_v4f32: |
| ; X64: # BB#0: |
| ; X64-NEXT: vandps {{.*}}(%rip), %xmm0, %xmm0 |
| ; X64-NEXT: retq |
| %t = call <4 x float> @llvm.fabs.v4f32(<4 x float> %p) |
| ret <4 x float> %t |
| } |
| declare <4 x float> @llvm.fabs.v4f32(<4 x float> %p) |
| |
| define <4 x double> @fabs_v4f64(<4 x double> %p) { |
| ; X32-LABEL: fabs_v4f64: |
| ; X32: # BB#0: |
| ; X32-NEXT: vandpd .LCPI2_0, %ymm0, %ymm0 |
| ; X32-NEXT: retl |
| ; |
| ; X64-LABEL: fabs_v4f64: |
| ; X64: # BB#0: |
| ; X64-NEXT: vandpd {{.*}}(%rip), %ymm0, %ymm0 |
| ; X64-NEXT: retq |
| %t = call <4 x double> @llvm.fabs.v4f64(<4 x double> %p) |
| ret <4 x double> %t |
| } |
| declare <4 x double> @llvm.fabs.v4f64(<4 x double> %p) |
| |
| define <8 x float> @fabs_v8f32(<8 x float> %p) { |
| ; X32-LABEL: fabs_v8f32: |
| ; X32: # BB#0: |
| ; X32-NEXT: vandps .LCPI3_0, %ymm0, %ymm0 |
| ; X32-NEXT: retl |
| ; |
| ; X64-LABEL: fabs_v8f32: |
| ; X64: # BB#0: |
| ; X64-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0 |
| ; X64-NEXT: retq |
| %t = call <8 x float> @llvm.fabs.v8f32(<8 x float> %p) |
| ret <8 x float> %t |
| } |
| declare <8 x float> @llvm.fabs.v8f32(<8 x float> %p) |
| |
| ; PR20354: when generating code for a vector fabs op, |
| ; make sure that we're only turning off the sign bit of each float value. |
| ; No constant pool loads or vector ops are needed for the fabs of a |
| ; bitcasted integer constant; we should just return an integer constant |
| ; that has the sign bits turned off. |
| ; |
| ; So instead of something like this: |
| ; movabsq (constant pool load of mask for sign bits) |
| ; vmovq (move from integer register to vector/fp register) |
| ; vandps (mask off sign bits) |
| ; vmovq (move vector/fp register back to integer return register) |
| ; |
| ; We should generate: |
| ; mov (put constant value in return register) |
| |
| define i64 @fabs_v2f32_1() { |
| ; X32-LABEL: fabs_v2f32_1: |
| ; X32: # BB#0: |
| ; X32-NEXT: xorl %eax, %eax |
| ; X32-NEXT: movl $2147483647, %edx # imm = 0x7FFFFFFF |
| ; X32-NEXT: retl |
| ; |
| ; X64-LABEL: fabs_v2f32_1: |
| ; X64: # BB#0: |
| ; X64-NEXT: movabsq $9223372032559808512, %rax # imm = 0x7FFFFFFF00000000 |
| ; X64-NEXT: retq |
| %bitcast = bitcast i64 18446744069414584320 to <2 x float> ; 0xFFFF_FFFF_0000_0000 |
| %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %bitcast) |
| %ret = bitcast <2 x float> %fabs to i64 |
| ret i64 %ret |
| } |
| |
| define i64 @fabs_v2f32_2() { |
| ; X32-LABEL: fabs_v2f32_2: |
| ; X32: # BB#0: |
| ; X32-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF |
| ; X32-NEXT: xorl %edx, %edx |
| ; X32-NEXT: retl |
| ; |
| ; X64-LABEL: fabs_v2f32_2: |
| ; X64: # BB#0: |
| ; X64-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF |
| ; X64-NEXT: retq |
| %bitcast = bitcast i64 4294967295 to <2 x float> ; 0x0000_0000_FFFF_FFFF |
| %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %bitcast) |
| %ret = bitcast <2 x float> %fabs to i64 |
| ret i64 %ret |
| } |
| |
| declare <2 x float> @llvm.fabs.v2f32(<2 x float> %p) |