forked from OSchip/llvm-project
e9ca7ea3e5
icmp ne (and X, 1), 0 --> trunc X to N x i1 Ideally, we'd do the same for scalars, but there will likely be regressions unless we add more trunc folds as we're doing here for vectors. The motivating vector case is from PR37549: https://bugs.llvm.org/show_bug.cgi?id=37549 define <4 x float> @bitwise_select(<4 x float> %x, <4 x float> %y, <4 x float> %z, <4 x float> %w) { %c = fcmp ole <4 x float> %x, %y %s = sext <4 x i1> %c to <4 x i32> %s1 = shufflevector <4 x i32> %s, <4 x i32> undef, <4 x i32> <i32 0, i32 0, i32 1, i32 1> %s2 = shufflevector <4 x i32> %s, <4 x i32> undef, <4 x i32> <i32 2, i32 2, i32 3, i32 3> %cond = or <4 x i32> %s1, %s2 %condtr = trunc <4 x i32> %cond to <4 x i1> %r = select <4 x i1> %condtr, <4 x float> %z, <4 x float> %w ret <4 x float> %r } Here's a sampling of the vector codegen for that case using mask+icmp (current behavior) vs. trunc (with this patch): AVX before: vcmpleps %xmm1, %xmm0, %xmm0 vpermilps $80, %xmm0, %xmm1 ## xmm1 = xmm0[0,0,1,1] vpermilps $250, %xmm0, %xmm0 ## xmm0 = xmm0[2,2,3,3] vorps %xmm0, %xmm1, %xmm0 vandps LCPI0_0(%rip), %xmm0, %xmm0 vxorps %xmm1, %xmm1, %xmm1 vpcmpeqd %xmm1, %xmm0, %xmm0 vblendvps %xmm0, %xmm3, %xmm2, %xmm0 AVX after: vcmpleps %xmm1, %xmm0, %xmm0 vpermilps $80, %xmm0, %xmm1 ## xmm1 = xmm0[0,0,1,1] vpermilps $250, %xmm0, %xmm0 ## xmm0 = xmm0[2,2,3,3] vorps %xmm0, %xmm1, %xmm0 vblendvps %xmm0, %xmm2, %xmm3, %xmm0 AVX512f before: vcmpleps %xmm1, %xmm0, %xmm0 vpermilps $80, %xmm0, %xmm1 ## xmm1 = xmm0[0,0,1,1] vpermilps $250, %xmm0, %xmm0 ## xmm0 = xmm0[2,2,3,3] vorps %xmm0, %xmm1, %xmm0 vpbroadcastd LCPI0_0(%rip), %xmm1 ## xmm1 = [1,1,1,1] vptestnmd %zmm1, %zmm0, %k1 vblendmps %zmm3, %zmm2, %zmm0 {%k1} AVX512f after: vcmpleps %xmm1, %xmm0, %xmm0 vpermilps $80, %xmm0, %xmm1 ## xmm1 = xmm0[0,0,1,1] vpermilps $250, %xmm0, %xmm0 ## xmm0 = xmm0[2,2,3,3] vorps %xmm0, %xmm1, %xmm0 vpslld $31, %xmm0, %xmm0 vptestmd %zmm0, %zmm0, %k1 vblendmps %zmm2, %zmm3, %zmm0 {%k1} AArch64 before: fcmge v0.4s, v1.4s, v0.4s zip1 v1.4s, v0.4s, v0.4s zip2 v0.4s, v0.4s, v0.4s orr v0.16b, v1.16b, v0.16b movi v1.4s, #1 and v0.16b, v0.16b, v1.16b cmeq v0.4s, v0.4s, #0 bsl v0.16b, v3.16b, v2.16b AArch64 after: fcmge v0.4s, v1.4s, v0.4s zip1 v1.4s, v0.4s, v0.4s zip2 v0.4s, v0.4s, v0.4s orr v0.16b, v1.16b, v0.16b bsl v0.16b, v2.16b, v3.16b PowerPC-le before: xvcmpgesp 34, 35, 34 vspltisw 0, 1 vmrglw 3, 2, 2 vmrghw 2, 2, 2 xxlor 0, 35, 34 xxlxor 35, 35, 35 xxland 34, 0, 32 vcmpequw 2, 2, 3 xxsel 34, 36, 37, 34 PowerPC-le after: xvcmpgesp 34, 35, 34 vmrglw 3, 2, 2 vmrghw 2, 2, 2 xxlor 0, 35, 34 xxsel 34, 37, 36, 0 Differential Revision: https://reviews.llvm.org/D52747 llvm-svn: 344082 |
||
|---|---|---|
| .. | ||
| AggressiveInstCombine | ||
| Coroutines | ||
| Hello | ||
| IPO | ||
| InstCombine | ||
| Instrumentation | ||
| ObjCARC | ||
| Scalar | ||
| Utils | ||
| Vectorize | ||
| CMakeLists.txt | ||
| LLVMBuild.txt | ||