Lines Matching refs:float

50     define float @my_fmad(float %x, float %y, float %z) {
51       %mul = fmul float %x, %y
52       %add = fadd float %mul, %z
53       ret float %add
56     define void @my_kernel(float* %ptr) {
57       %val = load float, float* %ptr
58       %ret = call float @my_fmad(float %val, float %val, float %val)
59       store float %ret, float* %ptr
64     !1 = !{void (float*)* @my_kernel, !"kernel", i32 1}
285   float my_function(float a) {
433   define void @kernel(float addrspace(1)* %A,
434                       float addrspace(1)* %B,
435                       float addrspace(1)* %C) {
441     %ptrA = getelementptr float, float addrspace(1)* %A, i32 %id
442     %ptrB = getelementptr float, float addrspace(1)* %B, i32 %id
443     %ptrC = getelementptr float, float addrspace(1)* %C, i32 %id
446     %valA = load float, float addrspace(1)* %ptrA, align 4
447     %valB = load float, float addrspace(1)* %ptrB, align 4
450     %valC = fadd float %valA, %valB
453     store float %valC, float addrspace(1)* %ptrC, align 4
459   !0 = !{void (float addrspace(1)*,
460                float addrspace(1)*,
461                float addrspace(1)*)* @kernel, !"kernel", i32 1}
610   !0 = !{void (float addrspace(1)*,
611                float addrspace(1)*,
612                float addrspace(1)*)* @kernel, !"kernel", i32 1}
697     checkCudaErrors(cuMemAlloc(&devBufferA, sizeof(float)*16));
698     checkCudaErrors(cuMemAlloc(&devBufferB, sizeof(float)*16));
699     checkCudaErrors(cuMemAlloc(&devBufferC, sizeof(float)*16));
701     float* hostA = new float[16];
702     float* hostB = new float[16];
703     float* hostC = new float[16];
707       hostA[i] = (float)i;
708       hostB[i] = (float)(2*i);
712     checkCudaErrors(cuMemcpyHtoD(devBufferA, &hostA[0], sizeof(float)*16));
713     checkCudaErrors(cuMemcpyHtoD(devBufferB, &hostB[0], sizeof(float)*16));
734     checkCudaErrors(cuMemcpyDtoH(&hostC[0], devBufferC, sizeof(float)*16));
815   declare float @__nv_powf(float, float)
817   define void @kernel(float addrspace(1)* %A,
818                       float addrspace(1)* %B,
819                       float addrspace(1)* %C) {
825     %ptrA = getelementptr float, float addrspace(1)* %A, i32 %id
826     %ptrB = getelementptr float, float addrspace(1)* %B, i32 %id
827     %ptrC = getelementptr float, float addrspace(1)* %C, i32 %id
830     %valA = load float, float addrspace(1)* %ptrA, align 4
831     %valB = load float, float addrspace(1)* %ptrB, align 4
834     %valC = call float @__nv_powf(float %valA, float %valB)
837     store float %valC, float addrspace(1)* %ptrC, align 4
843   !0 = !{void (float addrspace(1)*,
844                float addrspace(1)*,
845                float addrspace(1)*)* @kernel, !"kernel", i32 1}